Keywords: Visual Navigation, Localization, Computer Vision
Abstract: In outdoor environments shadows are common. These typically strong visual features cause considerable change in the appearance of a place, and therefore confound vision-based localisation approaches. In this paper we describe how to convert a colour image of the scene to a greyscale invariant image where pixel values are a function of underlying material property not lighting. We summarise the theory of shadow invariant images and discuss the modelling and calibration issues which are important for non-ideal off-the-shelf colour cameras. We evaluate the technique with a commonly used robotic camera and an autonomous car operating in an outdoor environment, and show that it can outperform the use of ordinary greyscale images for the task of visual localisation.

Keywords: Visual Navigation, Computer Vision, Localization
Abstract: Visual odometry (VO) is a highly efficient and powerful 6D motion estimation technique; state-of-the-art bundle adjustment algorithms now optimize over several frames of temporally tracked, appearance-based features in real time. It is well known that the temporal feature correspondence process is highly prone to mismatches. The standard technique used for outlier rejection in this process is random sample consensus (RANSAC), which is an iterative and non-deterministic process used to find the parameters of a mathematical model that best describe a likely set of inliers. The traditional model used for RANSAC in the visual odometry pipeline is a rigid transformation between two camera poses; this model has long assumed the use of an imaging sensor with a global shutter. In order to use imaging sensors that do not operate with a global shutter, it is proposed that the RANSAC algorithm be modified to use a constant-camera-velocity model. Specifically, this paper investigates the use of a two-axis scanning lidar in the visual-odometry pipeline. Images are formed using lidar intensity data, and due to the scanning-while-moving nature of the lidar, the behaviour of the sensor resembles that of a slow rolling-shutter camera. We formulate a Motion-Compensated RANSAC algorithm that uses a constant-velocity model and the individual timestamp of each extracted feature. The algorithm is validated using 6880 lidar frames with a resolution of 480x360, captured at 2Hz, over a 1.1km traversal. Our results show that the new algorithm results in far more inlying feature tracks for rolling-shutter-type images and ultimately higher-accuracy VO results.

Keywords: Visual Navigation, SLAM, Computer Vision
Abstract: In this paper, we propose a dense visual SLAM method for RGB-D cameras that minimizes both the photometric and the depth error over all pixels. In contrast to sparse, feature-based methods, this allows us to better exploit the available information in the image data which leads to higher pose accuracy. Furthermore, we propose an entropy-based similarity measure for keyframe selection and loop closure detection. From all successful matches, we build up a graph that we optimize using the g2o framework. We evaluated our approach extensively on publicly available benchmark datasets, and found that it performs well in scenes with low texture as well as low structure. In direct comparison to several state-of-the-art methods, our approach yields a significantly lower trajectory error. We release our software as open-source.

Keywords: Visual Navigation, SLAM, Aerial Robotics
Abstract: The navigation of a miniature aerial vehicle (MAV) in GPS-denied environments requires a robust embedded visual localization method.

In this paper, we describe a simple but efficient stereo visual odometry algorithm, called eVO, running onboard our quadricopter MAV at video-rate.

The proposed eVO algorithm relies on a keyframe scheme which allows to decrease the estimation drift and to reduce the computational cost. We study quantitatively the influence of the main parameters of the algorithm and tune them for optimal performance on various datasets.

The eVO algorithm has been submitted to the KITTI odometry benchmark~cite{Geiger12} where it ranks first at the date of submission, with an average translational drift of 1.93% and an average angular drift of less than 0.076 degres/m.

Besides, we have made several experiments with our MAV with egolocalization given by eVO, for instance for autonomous 3D environment modelling.

Keywords: Visual Navigation, Unmanned Aerial Vehicles, Computer Vision
Abstract: Achieving a robust, accurately scaled pose estimate in long range stereo presents significant challenges. For large scene depths, triangulation from a single stereo pair is inadequate and noisy. Additionally, vibration and flexible rigs in airborne applications mean accurate calibrations are often compromized. This paper presents a technique for accurately initializing a long range stereo VO algorithm at large scene depth, with accurate scale, without explicitly computing structure from rigidly fixed camera pairs. By performing a monocular pose estimate over a window of frames from a single camera, followed by adding the secondary camera frames in a modified bundle adjustment, an accurate, metrically scaled pose estimate can be found. To achieve this the scale of the stereo pair is included in the optimization as an additional parameter. Results are presented both on simulated and field gathered data from a fixed-wing UAV flying at significant altitude, where the epipolar geometry is inaccurate due to structural deformation and triangulation from a single pair is insufficient. Comparisons are made with more conventional VO techniques where the scale is not explicitly optimized, and demonstrated over repeated trials to indicate robustness.

Keywords: Visual Navigation, Visual Learning, Learning and Adaptive Systems
Abstract: As researchers are striving for developing robotic systems able to move into the ’the wild’, the interest towards novel learning paradigms for domain adaptation has increased. In the specific application of semantic place recognition from cameras, supervised learning algorithms are typically adopted. However, once learning has been performed, if the robot is moved to another location, the acquired knowledge may be not useful, as the novel scenario can be very different from the old one. The obvious solution would be to retrain the model updating the robot internal representation of the environment. Unfortunately this procedure involves a very time consuming data-labeling effort at the human side. To avoid these issues, in this paper we propose a novel transfer learning approach for place categorization from visual cues. With our method the robot is able to decide automatically if and how much its internal knowledge is useful in the novel scenario. Differently from previous approaches, we consider the situation where the old and the novel scenario may differ significantly (not only the visual room appearance changes but also different room categories are present). Importantly, our approach does not require labeling from a human operator. We also propose a strategy for improving the performance of the proposed method by fusing two complementary visual cues. Our extensive experimental evaluation demonstrates the advantages of our approach on several sequences from publicly available datasets.

Keywords: Surveillance Systems, Computer Vision, Recognition
Abstract: In many intelligent surveillance systems there is a requirement to search for people of interest through archived semantic labels. Other than searching through typical appearance attributes such as clothing color and body height, information such as whether a person carries a bag or not is valuable to provide more relevant targeted search. We propose two novel and fast algorithms for sling bag and backpack detection based on the geometrical properties of bags. The advantage of the proposed algorithms is that it does not require shape information from human silhouettes therefore it can work under crowded condition. In addition, the absence of background subtraction makes the algorithms suitable for mobile platforms such as robots. The system was tested with a low resolution surveillance video dataset. Experimental results demonstrate that our method is promising.

Attachments: Video Attachment
Keywords: Computer Vision, Grasping, Human-Robot Interaction
Abstract: We present a real-time algorithm that segments unstructured and highly cluttered scenes. The algorithm robustly separates objects of unknown shape in congested scenes of stacked and occluded objects. The model-free approach finds smooth surface patches, using a depth image from a Kinect camera, which are subsequently combined to form highly probable object hypotheses. Coplanarity and curvature matching is used to recombine surfaces separated by occlusion. The real-time capabilities are proven and the quality of the algorithm is evaluated on a benchmark database. Advantages compared to existing approaches as well as weaknesses are discussed.

Keywords: Visual Tracking, Computer Vision
Abstract: We propose a method for tracking the bound- ary of an object at frame rates beyond 1 kHz, based on a novel contour propagation mechanism operating in polar image space. The work draws inspiration from well established methodologies in object tracking and segmentation. The main contribution is how the polar representation is exploited for tracking, including enabling parallelization for sub millisecond performance. The presented results show the feasibility of the method in a wide range of settings.

Keywords: Omnidirectional Vision, Recognition, Computer Vision
Abstract: We describe a system that recognizes human postures with heavy self-occlusion. In particular, we address posture recognition in a robot assisted-living scenario, where the environment is equipped with a top-view camera for monitoring human activities. This setup is very useful because top-view cameras lead to accurate localization and limited inter-occlusion between persons, but conversely they suffer from body parts being frequently self-occluded. The conventional way of posture recognition relies on good estimation of body part positions, which turns out to be unstable in the top-view due to occlusion and foreshortening. In our approach, we learn a posture descriptor for each specific posture category. The posture descriptor encodes how well the person in the image can be ‘explained’ by the model. The postures are subsequently recognized from the matching scores returned by the posture descriptors. We select the state-of-the-art approach of pose estimation as our posture descriptor. The results show that our method is able to correctly classify 79.7% of the test sample, which outperforms the conventional approach by over 23%.

Keywords: Computer Vision, Range Sensing, Recognition
Abstract: A new system for object detection in cluttered RGB-D images is presented. Our main contribution is a new method called Bingham Procrustean Alignment (BPA) to align models with the scene. BPA uses point correspondences between oriented features to derive a probability distribution over possible model poses. The orientation component of this distribution, conditioned on the position, is shown to be a Bingham distribution. This result also applies to the classic problem of least-squares alignment of point sets, when point features are orientation-less, and gives a principled, probabilistic way to measure pose uncertainty in the rigid alignment problem. Our detection system leverages BPA to achieve more reliable object detections in clutter.

Keywords: Automation in Life Sciences: Biotechnology, Pharmaceutical and Health Care, Computer-assisted diagnosis and therapy, Human detection and tracking
Abstract: Presented are results demonstrating that, in developing a system with its first objective being the sustained detection of adults and young children as they move and interact in a normal preschool setting, the direct application of the straightforward RGB-D innovations presented here significantly outperforms even far more algorithmically advanced methods relying solely on images. The use of multiple RGB-D sensors by this project for depth-aware object localization economically resolves numerous issues regularly frustrating earlier vision-only detection and human surveillance methods, issues such as occlusions, illumination changes, unexpected postures, atypical morphologies, erratic or unanticipated motions, reflections, and misleading textures and colorations. This multiple RGB-D installation forms the front-end for a multi-step pipeline, the first portion of which seeks to isolate, in situ, 3D renderings of classroom occupants sufficient for a later analysis of their behaviors and interactions. Towards this end, a voxel-based approach to foreground/background separation and an effective adaptation of supervoxel clustering for 3D were developed, and 3D and image-only methods were tested and compared. The project’s setting is highly challenging, but then so are its longer term goals: the automated detection of early childhood precursors, ofttimes very subtle, to a number of increasingly common developmental disorders.

Keywords: Human-Robot Interaction, Robot Companions and Social Human-Robot Interaction, Learning and Adaptive Systems
Abstract: The increasing use of mobile robots in social contexts makes it important to provide them with the ability to behave in the most socially acceptable way possible. In this paper we investigate the problem of making a robot learn how to approach a person in order to increase the chance of a successful engagement. We propose the use of Gaussian Process Regression (GPR), combined with ideas from reinforcement learning to make sure the space is properly and continuously explored. In the proposed example scenario, this is used by the robot to predict the best decisions in relation to its position in the environment and approach distance, each one accordingly to a certain time of the day. Numerical simulations show a significant performance improvement when compared with a random technique. The robot is able to improve performance after just one day of interaction (a few dozens of trials), and achieves the maximum expected value for the proposed approach within sixty days.

Keywords: Human-Robot Interaction, Cognitive Human-Robot Interaction, Robot Companions and Social Human-Robot Interaction
Abstract: Analyzing affordances has its root in socio-cognitive development of primates. Knowing what the environment, including other agents, can offer in terms of action capabilities is important for our day-to-day interaction and cooperation. In this paper, we will merge two complementary aspects of affordances: from agent-object perspective, what an agent afford to do with an object, and from agent-agent perspective, what an agent can afford to do for other agent, and present a unified notion of Affordance Graph. The graph will encode affordances for a variety of tasks: take, give, pick, put on, put into, show, hide, make accessible, etc. Another novelty will be to incorporate the aspects of effort and perspective-taking in constructing such graph. Hence, the Affordance Graph will tell about the action-capabilities of manipulating the objects among the agents and across the places, along with the information about the required level of efforts and the potential places. We will also demonstrate some interesting applications.

Keywords: Human-Robot Interaction
Abstract: Facial expressions are a rich source of communicative information about human behavior and emotion. This paper presents a real-time system for recognition and imitation of facial expressions in the context of affective Human Robot Interaction. The proposed method achieves a fast and robust facial feature extraction based on consecutively applying filters to the gradient image. An efficient Gabor filter is used, along with a set of morphological and convolutional filters to reduce the noise and the light dependence of the image acquired by the robot. Then, a set of invariant edge-based features are extracted and used as input to a Dynamic Bayesian Network classifier in order to estimate a human emotion. The output of this classifier updates a geometric robotic head model, which is used as a bridge between the human expressiveness and the robotic head. Experimental results demonstrate the accuracy and robustness of the proposed approach compared to similar systems.

Keywords: Human-Robot Interaction, Computer Vision, Behaviour-Based Systems
Abstract: Recent research in HRI has emphasized the need to design affective interaction systems equipped with social intelligence. A robot's awareness of its social role encompasses the ability to behave in a socially acceptable manner, the ability to communicate appropriately according to the situation, and the ability to detect the feelings of interactive partners, as humans do with one another. In this paper, we propose an intelligent robotic method of attracting a target person's attention in a way congruent to satisfying these social requirements. If the robot needs to initiate communication urgently, such as in the case of reporting an emergency, it does not need to consider the current situation of the person it is addressing. Otherwise, the robot should observe the person to ascertain who or what s/he is looking at (VFOA), and how attentively s/he is doing so (VFOA level). Moreover, the robot must identify an appropriate time at which to attract the target person's attention so as to not interfere with his/her work. We have realized just such a robotic system by developing computer vision methods to detect a target person's VFOA and its level, and testing the system's effectiveness in a series of experiments.

Attachments: Video Attachment
Keywords: Human-Robot Interaction, Visual Servoing
Abstract: For intuitive human-robot collaboration, the robot must quickly adapt to the human behavior. To this end, we propose a multimodal sensor-based control framework, enabling a robot to recognize human intention, and consequently adapt its control strategy. Our approach is marker-less, relies on a Kinect and on an on-board camera, and is based on a unified task formalism. Moreover, we validate it in a mock-up industrial scenario, where human and robot must collaborate to insert screws in a flank.

Attachments: Video Attachment
Keywords: Human-Robot Interaction, Gesture, Posture, Social Spaces and Facial Expressions
Abstract: Human safety and effective human-robot communication are main concerns in HRI applications. In order to achieve such goals, a system should be very robust, allowing little chance for misunderstanding the user’s commands. Moreover, the system should permit natural interaction reducing the time and the effort needed to achieve tasks. The main purpose of this work is to develop a general framework for flexible and multimodal human-robot communication. The proposed architecture should be easy to modify and expand, adding or modifying input channels and changing the multimodal fusion strategies. In this paper, we introduce our general approach and provide a case study with two modalities (gesture and speech).

Keywords: Recognition, Computer Vision
Abstract: Despite the rich information provided by sensors such as the Microsoft Kinect in the robotic perception setting, the problem of detecting object instances remains unsolved, even in the tabletop setting, where segmentation is greatly simplified. Existing object detection systems often focus on textured objects, for which local feature descriptors can be used to reliably obtain correspondences between different views of the same object. We examine the benefits of dense feature extraction and multimodal features for improving the accuracy and robustness of an instance recognition system. By combining multiple modalities and blending their scores through an ensemble- based method in order to generate our final object hypotheses, we obtain significant improvements over previously published results on two RGB-D datasets. On the Challenge dataset, our method results in only one missed detection (achieving 100% precision and 99.77% recall). On the Willow dataset, we also make significant gains on the prior state of the art (achieving 98.28% precision and 87.78% recall), resulting in an increase in F-score from 0.8092 to 0.9273.

Keywords: Recognition, Domestic Robots and Home Automation, Gesture, Posture, Social Spaces and Facial Expressions
Abstract: In this paper, we propose a Bayesian conditional probability with latent-structure model for context-aware activities of daily living (ADL) recognition. The proposed ADL recognition system takes RGBD sensor (Microsoft Kinect) as the input device. In ADL recognition, the object interacted with human is a sort of important context as well as human action. To better under-stand the activity, we model the interacted object and the human action together. As far as we known, many related works failed to take into account the relation between the context information and human action features, instead, most of them only consider the human action features, causing ambiguity in classifying the activities with similar human actions. In this paper, the context information and human action features are taken into consideration, concurrently, so that the performance of recognition can be greatly improved from previous works as has been demonstrated in our experimental results.

Keywords: Recognition
Abstract: We present an approach to create a semantic map of an indoor environment, based on a series of 3D point clouds captured by a mobile robot using a Kinect camera. The proposed system reconstructs the surfaces in the point clouds, detects different types of furniture and estimates their pose. The result is a consistent mesh representation of the environment enriched by CAD models corresponding to the detected pieces of furniture. We evaluate our approach on two datasets totaling over 800 frames directly on each individual frame.

Keywords: Recognition, Computer Vision, Human-Robot Interaction
Abstract: In this paper, we propose an efficient part-based approach for action recognition. The main concept is to recognize human actions by less occluded parts without using a large set of part filters. Therefore, our approach is robust to occlusion and cost-effective. We extract spatio-temporal features from RGB-D videos, and assign a part-label to each feature. Then, for each part, a recognition score is computed for each action class by pyramid-structural bag of words (BoW-Pyramid) representation. The final result is determined by weighted sum of these scores and contextual information, which is based on the ratio of features between every pair of parts. Several contributions have been made in this work. First, the proposed part-based method is robust to occlusion and operates on-line. Second, our BoW-Pyramid representation can distinguish actions with re-versed temporal orders. Third, recognition accuracy is increased by incorporating contextual information. The provided experimental results have verified effectiveness of our method and demonstrated high promise of surpassing performance of the state-of-the-art works.

Keywords: Recognition, Visual Learning, Computer Vision
Abstract: Most object classes share a considerable amount of local appearance and often only a small number of features are discriminative. The traditional approach to represent an object is based on a summarization of the local characteristics by counting the number of feature occurrences. In this paper we propose the use of a recently developed technique for summarizations that, rather than looking into the quantity of features, encodes their quality to learn a description of an object. Our approach is based on extracting and aggregating only the essential characteristics of an object class for a task. We show how the proposed method significantly improves on previous work in 3D object categorization. We discuss the benefits of the method in other scenarios such as robot grasping. We provide extensive quantitative and qualitative experiments comparing our approach to the state of the art to justify the described approach.

Attachments: Video Attachment
Keywords: Recognition, Visual Learning, Industrial Robots
Abstract: We present an approach for object class learning using a part-based shape categorization in RGB-augmented 3D point clouds captured from cluttered indoor scenes with a Kinect-like sensor. A graph representation is used to detect and categorize object instances based on part-constellations found in scenes. No assumptions like objects being placed on planar surfaces or constraints on their poses are required. Our approach consists of the following steps: 1) a Mean-Shift-based over-segmentation of a point cloud into atomic patches; 2) use of topological and geometric features to merge surface-homogeneous atomic patches into super patches; 3) an unsupervised classification of these parts that allows to symbolically label distinctively unknown object parts by their surface-structural appearance; and finally, 4) a graph generation procedure that reflects the constellation of the detected parts from object instances of certain shape categories. Furthermore, an inference procedure is presented that processes extracted part constellations of a scene to detect and categorize object instances. Experiments with challenging, cluttered scenes show that the segmentation procedure provides salient parts of objects which lead to a good categorization performance using the graph-based constellation model concept.

Keywords: Learning and Adaptive Systems, Visual Learning, Recognition
Abstract: The human understanding of things is based on prediction which is made through concepts formed by the categorization of experience. To mimic this mechanism in robots, multimodal categorization, which enables the robot to form concepts, has been studied. On the other hand, segmentation and categorization of human motions have also been studied to recognize and predict future motions. This paper addresses the issue on how these different kinds of concepts are integrated to generate higher level concepts and, more importantly, on how the higher level concepts affect the formation of each lower level concept. To this end, we propose the multi-layered multimodal latent Dirichlet allocation (mMLDA), which is an expansion of the MLDA to learn and represent the hierarchical structure of concepts. We also examine a simple integration model and compare it with the mMLDA. The experimental results reveal that the mMLDA leads to a better inference performance and, indeed, forms higher level concepts which integrate motions and objects that are necessary for real-world understanding.

Keywords: Visual Learning, Computer Vision, Perception for Grasping and Manipulation
Abstract: Learning about activities and object affordances from human demonstration are important cognitive capabilities for robots functioning in human environments, for example, being able to classify objects and knowing how to grasp them for different tasks. To achieve such capabilities, we propose a Labeled Multi-modal Latent Dirichlet Allocation (LM-LDA), which is a generative classifier trained with two different data cues, for instance, one cue can be traditional visual observation and another cue can be contextual information. The novel aspects of the LM-LDA classifier, compared to other methods for encoding contextual information are that, I) even with only one of the cues present at execution time, the classification will be better than single cue classification since cue correlations are encoded in the model, II) one of the cues (e.g., common grasps for the observed object class) can be inferred from the other cue (e.g., the appearance of the observed object). This makes the method suitable for robot online and transfer learning; a capability highly desirable in cognitive robotic applications. Our experiments show a clear improvement for classification and a reasonable inference of the missing data.

Keywords: Learning and Adaptive Systems, Visual Learning, Recognition
Abstract: In recent studies, it has been revealed that robots can form concepts and understand the meanings of words through inference. The key idea underlying these studies is “multimodal categorization” of a robot’s experience. However, previous studies considered only nonhierarchical categorization methods, which led to nonhierarchical concept structures. Our concepts have a hierarchical structure, thus ensuring that the resulting inferences are more efficient and accurate. In this paper, we propose a novel hierarchical categorization method. The method involves extending multimodal latent Dirichlet allocation (MLDA) to hierarchical MLDA using the nested Chinese restaurant process, which makes it possible for robots to acquire concepts in a hierarchical structure. We show that a robot can form a hierarchical concept structure based on self-obtained multimodal information. Moreover, by focusing on the common features of each category in the hierarchy, the robot is able to infer unobserved information including word meanings.

Keywords: Learning and Adaptive Systems, Human-Robot Interaction, Cognitive Human-Robot Interaction
Abstract: One of the biggest challenges in intelligent robotics is to build robots that can understand and use language. Such robots will be a part of our everyday life; at the same time, they can be of great help to investigate the complex mechanism of language acquisition by infants in constructive approach. To this end, we think that the practical long-term on-line concept/word learning algorithm for robots and the interactive learning framework are the key issues to be addressed. In this paper we develop a practical on-line learning algorithm that solves three remaining problems in our previous study. We also propose an interactive learning framework, in which the proposed on-line learning algorithm is embedded. The main contribution of this paper is to develop such a practical learning framework, and we test it on a real robot platform to show its potential toward the ultimate goal.

Keywords: Learning and Adaptive Systems, Autonomous Agents, Humanoid Robots
Abstract: An affordance is a relation between an object, an action, and the effect of that action in a given environmental context. One key benefit of the concept of affordance is that it provides information about the consequence of an action which can be stored and reused in a range of tasks that a robot needs to learn and perform. In this paper, we address the challenge of the on-line learning and use of affordances simultaneously while performing goal-directed tasks. This requires efficient on-line performance to ensure the robot is able to achieve its goal fast. By providing conceptual knowledge of action possibilities and desired effects, we show that a humanoid robot NAO can learn and use affordances in two different task settings. We demonstrate the effectiveness of this approach by integrating affordances into an Extended Classifier System for learning general rules in a reinforcement learning framework. Our experimental results show significant speedups in learning how a robot solves a given task.

Keywords: Learning and Adaptive Systems, Integrated Planning and Control, Control Architectures and Programming
Abstract: Robot motor skill learning is currently one of the most active research areas in robotics. Many learning techniques have been developed for relatively simple problems. However, very few of them have direct applicability in complex robotics systems without assuming prior knowledge about the task due to two facts. On one hand, they scale badly to continues and high dimensional problems. In the other hand, they require too many real learning episodes. In this sense, this paper provides a detailed description of an original approach capable of learning from scratch suboptimal solutions and of providing close-loop motor control policies in the proximity of such solutions. The developed architecture manages the solution in two consecutive phases. The first phase provides an initial open-loop solution state-action trajectory by mixing kinodynamic planning with model learning. In the second phase, the initial state trajectory solution is first smoothed and then, a close-loop controller with active learning capabilities is learned in its proximity. We will demonstrate the efficiency of this two phases approach in the Cart-Pole Swing-Up Task problem.

Attachments: Video Attachment
Keywords: Climbing robots, Agent-Based Systems
Abstract: This paper presents a newly-designed robot named "Rubbot" dedicated to climbing on soft flexible clothes. Equipped with novel grippers which grip and rub on clothes, Rubbot is able to climb on flexible clothes and control how much fabric to grasp by feedback from infrared sensor. Rubbot also has a frame which has three passive folders which adjust the climbing posture of Rubbot. This not only makes Rubbot quite functional with clothes of different thicknesses and curved surfaces, but also makes Rubbot's motion more flexible. A theory of the deformation of cloth is then presented based on an analysis of creases created while Rubbot is climbing; this leads to a more reliable method to climb flexible surfaces. Finally experiments have verified that Rubbot is effective on flexible surfaces, as it can climb on 95% of the surfaces human clothes and still perform well on non-rigidly backed cloth.

Keywords: Climbing robots, Navigation, Robot Safety
Abstract: Safe navigation on vertical concrete structures is still a great challenge for mobile climbing robots. The main problem is to find the optimum of applicability and safety since these systems have to fulfill certain tasks without endangering persons or their environment. This paper addresses aspects of safe navigation in the range of wall-climbing robots using negative pressure adhesion in combination with a drive system. In this context aspects of the developed robot control architecture will be presented and common hazards for this type of robots are examined. Based on this analysis a risk prediction function is trained via methods of evolutionary algorithms based on internal data generated inside of the behavior-based robot control network. Although there will always be a residual risk of a robot drop-off it is shown that the risk could be lowered tremendously by the developed analysis methods and counteractive measures.

Attachments: Video Attachment
Keywords: Climbing robots, Mechanism Design
Abstract: In order to grasp and hold uneven or dusty objects, a robust adhesion mechanism is required. This paper evaluates controllable adhesion using magneto-rheological fluid (MRF) as a technique to stick to non-magnetic materials and rough/dusty surfaces. This technique is both simple to use and robust to uncertain surface conditions, as it involves applying MRF on a surface and activating it with a magnetic field. In this paper, we experimentally evaluate yield stresses in both normal and shear directions with respect to MRF layer thickness, magnetic flux density and surface type. Based on these results, a four-legged climbing robot is designed to demonstrate scaling vertical walls and shows effectiveness of the controllable adhesion using MRF for rough surface.

Keywords: Climbing robots, Animation and Simulation
Abstract: Simulation frameworks are wide-spread in the range of robotics to test algorithms and analyze system behavior beforehand -- which tremendously reduces effort and time needed for conducting experiments on the real machines. This paper addresses a framework for simulating a wall-climbing robot that uses negative pressure adhesion in combination with an omnidirectional drive system. Key aspect is the adhesion system which interacts with the environmental features such as surface characteristics (like roughness) or defects. This system consists of simulated pressure sensors, valves between adhesion chambers and vacuum reservoir and a simulated adaptive sealing proofing the vacuum chambers towards ambient air. An elaborate thermodynamic model provides the basis for a realistic simulation of the airflow between the virtual environment and the vacuum chambers of the robot. These features facilitate the validation of closed-loop controllers and control algorithms offline and in realtime.

Keywords: Climbing robots
Abstract: A model is presented for the analysis of the electric field and electrostatic adhesion force produced by interdigital electrodes. Assuming that the potential varies linearly with distance in inter-electrode gaps, the potential distribution on the electrode plane is obtained by taking the first-order Taylor series approximation. The expressions of electric filed components are then derived by solving the Laplace equation for the electrical potential in each subregion. The electrostatic adhesion force is calculated using the Maxwell stress tensor formulation. The dynamic properties of the electric field and electrostatic adhesion force are assessed by evaluating the transient response of the field and force under a step in applied voltages. To verify the model developed, an experimental study is carried out in conjunction with the theoretical analysis to evaluate the adhesion performance of an electrode panel on a glass pane. A double tracked wall climbing robot is designed and tested on various wall surfaces. The limit of the approximation method of the inter-electrode potential is discussed. It is found that vacuum suction force is involved in the adhesion. The influence of this vacuum suction force on electrostatic adhesion is also discussed. The results of this work would provide support for theoretical guidelines and system optimization for the electrostatic adhesion technology applied to wall climbing robots.

Keywords: Climbing robots, Mechanism Design
Abstract: This paper presents a wall-climbing robot for reconnaissance in anti-hijacking application. A novel biped-wheel hybrid locomotion mechanism is proposed, which is composed of a planetary gear train, a vacuum adhesion module and a negative pressure adhesion module. The bipedal, wheeled and hybrid locomotion modes are analyzed respectively. A prototype of the wall-climbing robot with compact size and low power consumption has been developed and a lot of performance tests have been conducted. The experimental results demonstrate that the wall-climbing robot has such characteristics as fast moving speed, excellent surface adaptability and obstacle negotiation capability.

Attachments: Video Attachment
Keywords: Dynamics, Mechanism Design, Motion Control
Abstract: SkySweeper is a mobile robot designed to operate in an environment of cables, wires, power lines, ropes, et cetera. The robot is comprised of two links pivotally connected at one end; a series elastic actuator at this “elbow” joint can actuate relative rotation between the two links. At the opposite end of each link is an actuated three-position clamp. The clamp can either be open, partially closed, such that the clamp can roll (translate) along the cable, or fully closed, such that the clamp can only pivot on the cable. By actuating the elbow joint and cleverly choosing the positions of the clamps, the robot can locomote on the cable in a number of different ways. The particular method of locomotion can be chosen to minimize energy consumption, maximize speed, or traverse an obstacle (e.g. a support from which the cable is suspended). SkySweeper has the potential to locomote in a more energy efficient manner than existing cable-locomoting robots. It also operates with a minimal number of actuators, which reduces cost significantly. Potential applications include power and communication line inspection, suspension bridge inspection and construction, as well as entertainment. Data from a prototype, consisting largely of 3D-printed and off-the-shelf parts, are compared to dynamic simulation results.

Keywords: Dynamics, Legged Robots
Abstract: Stable locomotion indicates a stable limit cycle generated in the dynamic system. Although quadrupedal bound gait models have been investigated, there is no research which shows the generation of limit cycle and its dynamic properties. In the present study, we analyze a quadrupedal bound gait model which goes down slope and has back and front bodies with spring-damper joint between the bodies. We found the periodic bound gait which achieves a stable limit cycle and convergence property against perturbations.

Keywords: Dynamics, Human and humanoid skills/cognition/interaction, Humanoid Robots
Abstract: This paper reports the result and discussion about our second experiment of standing motion measurement and analysis. We aim at identifying the standing controller of a human. In order to tackle the dynamical complexity of the human body, the COM-ZMP (the center of mass and the zero-moment point) model, which is widely used for designing the whole-body controller of humanoid robots, and a piecewise-linear controller is applied. In the previous experiment, the authors proposed a method to collect a sufficient number of loci of COM in a phase space for the identification of a controller, and showed that the human's standing behavior qualitatively has a similar property with the COM-ZMP model. It was also found, however, that the collected loci had large variability due to the uncertainty of convergence point and were partially inconsistent with the model, so that it was still difficult to identify the controller. Then, the authors reassessed the model and measurement protocol, and conducted the second experiment in order to improve the reliability of the measurement by visually presenting the referential point to subjects and by redesigning the protocol. As the result, more reliable loci to be processed of identification were obtained. It was also found that the effect of variation of the COM height due to the limitation of leg length, which was thought to be another source of the inconsistency, certainly existed but was not critical to model the human behavior.

Keywords: Dynamics, Motion and Path Planning, Path Planning for Manipulators
Abstract: The algorithm for finding the time-optimal parameterization of a given path subject to dynamics constraints developed mostly in the 80's and 90's plays a central role in a number of important robotic theories and applications. A critical issue in its implementation is associated with the so-called dynamic singularities, i.e. the points where the maximum velocity curve is continuous but undifferentiable and where the minimum and maximum accelerations are not naturally defined. Since such singularities arise in most real-world problem instances, characterizing and addressing them appropriately is of particular interest. Yet, from original articles to reference textbooks, this has not yet been done completely correctly. The contribution of the present article is two-fold. First, we derive a complete characterization of dynamic singularities. In particular, we show that not all zero-inertia points are dynamically singular. Second, we suggest how to appropriately address these singularities. In particular, we derive the analytic expressions of the correct optimal backward and forward accelerations from such points.

Keywords: Dynamics, Kinematics, Humanoid Robots
Abstract: In this paper we review and extend some classic results on rigid body dynamics, in order to give a symbolic expression of the different derivatives of the matrices of the dynamic model of a general tree-structured robot. In what follows the matrices are differentiated with respect to time, state and dynamic parameters. Obviously from the derivatives of the single matrices it is possible to recover the derivatives of the direct and inverse dynamic functions and classic results like the regressor matrix. Moreover an iterative algorithm is sketched which allows to compute all these derivatives as well as the kinematics and dynamics of the robot.

Keywords: Dynamics, Industrial Robots
Abstract: Model-based control are affected by the accuracy of dynamic calibration. For industrial robots, identification techniques predominantly involve rigid body models linearized on a set of minimal lumped parameters that are estimated along excitatory trajectories made by suitable/optimal path. Although the physical meaning of the estimated lumped models is often lost (e.g. negative inertia values), these methodologies get remarkably results when well-conditioned trajectories are applied. Nonetheless, such trajectories have usually to span the workspace at large, resulting in an averagely fitting model. In many technological tasks, instead, the region of dynamics applications is limited, and generation of trajectories in such workspace sub-region results in different specialized models that should increase the predictability of local behavior. Besides this consideration, the paper presents a genetic-based selection of trajectories in constrained sub-region. The methodology places under optimization paths generated by a commercial industrial robot interpolator, and the genes (i.e. the degrees-of-freedom) of the evolutionary algorithms corresponds to a finite set of few via-points and velocities, just like standard motion programming of industrial robots. Remarkably, experiments demonstrate that this algorithm design feature allows a good matching of foreseen current and the actual measured in different task conditions.

Attachments: Video Attachment
Keywords: Motion and Path Planning, Medical Robots and Systems, Nonholonomic Motion Planning
Abstract: In this paper, we propose a new insertion plan for steerable flexible needles with which we can target multiple locations in the plane with a single entry point (i.e. port). The method is developed based on the observation that multiple locations can be reached by a flexible needle through insertion, partial retraction, rotation, and re-insertion of the needle. We show that in 2D space this problem can be solved using a geometric relationship between multiple tangent circles. Specifically we find a needle insertion point, a corresponding insertion direction and lengths for insertion and retraction with which we can generate the optimal needle trajectory that reaches two or three planar targets with the minimum tissue damage. This minimization problem is solved using exhaustive search of a cost function on the 1D bounded domain. We build a prototype of a needle insertion system and develop C#-based software to compute the optimal needle paths and perform the planned insertion as an open-loop controller. Finally, actual insertion examples are presented.

Keywords: Sensor-based Planning, Recognition, Autonomous Agents
Abstract: Active scene exploration incorporates object recognition methods for analyzing a scene of partially known objects and exploration approaches for autonomous modeling of unknown parts. In this work, recognition, exploration, and planning methods are extended and combined in a single scene exploration system, enabling advanced techniques such as multi-view recognition from planned view positions and iterative recognition by integration of new objects from a scene. Here, a geometry based approach is used for recognition, i.e. matching objects from a database. Unknown objects are autonomously modeled and added to the recognition database. Next-Best-View planning is performed both for recognition and modeling. Moreover, 3D measurements are merged in a Probabilistic Voxel Space, which is utilized for planning collision free paths, minimal occlusion views, and verifying the poses of the recognized objects against all previous information. Experiments on an industrial robot with attached 3D sensors are shown for scenes with household and industrial objects.

Keywords: Nonholonomic Motion Planning, Wheeled Robots, Collision Detection and Avoidance
Abstract: This paper presents a fast optimization based algorithm for car parking. The challenge arises from the non-holonomic characteristics of the car and the close distance to the obstacles. The presented approach utilizes the Minkowski sum to account for obstacle avoidance. The geometric path planning problem is decoupled from the kinematic problem and discretized with respect to the path parameter by means of a Runge-Kutta discretization. For the discrete path segments, an optimization problem is formulated to calculate the path independent of the parking scenario. This static optimization problem can be solved numerically in a very efficient way. The performance of the algorithm is evaluated in several simulation scenarios.

Keywords: Formal Methods in Robotics and Automation, Kinematics
Abstract: This paper presents a scene graph for geometric relations between rigid bodies that keeps track of poses and twists of rigid bodies in the scene. The scene graph relies on semantic pose and twist representation, making it invariant to the actual coordinate representation at hand. This makes the scene graph more general and interoperable than most scene graphs currently available. The presented scene graph takes into account constraints imposed by particular coordinate representations, allows for constant poses, answers semantic pose and twist queries, and provides built-in semantic consistency checks. Since the scene graph also keeps track of the twist, it allows native twist calculations, as opposed to deriving the velocities from the poses in the graph. This paper comes with software released under a dual BSD/LGPLv2.1 license.

Attachments: Video Attachment
Keywords: Motion and Path Planning, Planning, Scheduling and Coordination, Multi-Robot Coordination
Abstract: Manipulation and transport of objects using mobile robotic platforms is a well studied field with several successful approaches. The main difficulty while using such platforms is the lack of adaptation capabilities to changes in the environment and the restriction to flat working areas. In this paper, we present a novel manipulation and transport framework using the self-reconfigurable modular robots Roombots to collaboratively carry arbitrarily shaped passive elements in a non-regular 3D environment equipped with passive connectors. A hierarchical planner based on the notion of virtual kinematic chain is used to generate collision-free and hardware-friendly paths as well as sequences of collaborative manipulations. To the best of our knowledge, this is the first example of manipulation of fully passive elements in an arbitrary 3D environment using mobile self-reconfigurable robots. The simulated results show that the planner is robust to arbitrary complex environments with randomly distributed connectors. In addition to simulation results, a proof of concept of the manipulation of one passive element with two real Roombots meta-modules is described.

Keywords: Nonholonomic Motion Planning, Motion and Path Planning, Wheeled Robots
Abstract: The paper deals with the problem of motion planning for a spherical rolling robot actuated by two internal rotors that are placed on orthogonal axes. To solve the problem, we employ the so-called geometric phase approach based on the fact that tracing a closed path in the space of input variables results in a non-closed path in the space of output variables. To set up the governing equations, the contact kinematic equations are modified by the condition of dynamic realizability, which constrains the component of the angular velocity of the rolling carrier and depends on the mass distribution, and parameterized. By using a motion planning strategy based on tracing two circles on the spherical surface, an exact and dynamically realizable motion planning algorithm is fabricated and verified under simulation.

Keywords: Aerial Robotics, Motion Control, Unmanned Aerial Vehicles
Abstract: This paper presents the design and evaluation of a nonlinear control scheme for multirotor helicopters that takes first-order drag effects into account explicitly. A dynamic model including the blade flapping and induced drag forces is presented. Based on this model, a hierarchical nonlinear controller is designed to actively compensates for the nonlinear effects these drag forces. Reported simulation and experimental results indicate the significant performance improvement of the proposed drag-augmented control scheme with respect to a conventional nonlinear controller. For completeness, an offline procedure allowing for efficiently identifying the drag parameters is proposed.

Keywords: Unmanned Aerial Vehicles, Aerial Robotics, Motion Control
Abstract: Recently many researches have been studied to run autonomous flying vehicles. Especially, quadrotor VTOL (Vertical Take-Off and Landing) has been a challenging subject. To stabilize the quadrotor system, many control algorithms and sensor systems have been developed. Most of them are based on the sensors like accelerometer, gyroscope, or IMU (Inertial Measurement Unit) to measure the attitude of quadrotor. Instead of using these conventional sensors, we apply one vision sensor to stabilize the attitude of a quadrotor system. To achieve this, four laser diodes are evenly distributed in the bottom plane of quadrotor, and then point downwards. The positions of laser markers depend on the attitude and height of the quadrotor. We develop a control algorithm to stabilize the attitude as well as to control the height of a quadrotor. We show that the visual tracking of the laser markers is sufficient to estimate the state of the quadrotor attitude and control it into a desired state.

Keywords: Aerial Robotics, Localization, Unmanned Aerial Vehicles
Abstract: Given a hover-capable flying vehicle attached to a fixed point by a taut tether, we present a novel method to recover the vehicle's relative position and absolute orientation. The proposed method requires only on-board inertial sensors, and indirectly measures the string force, enabling the additional use of the tether as a physical user interaction medium. We present the vertical-plane dynamics of such a system and the localization approach, discuss sensitivity issues, and implement an estimator and controller based on the presented model. We demonstrate the method experimentally on a tethered quadrocopter in the Flying Machine Arena, using both a vertical-plane-constrained vehicle and in 3D.

Keywords: Aerial Robotics, Adaptive Control
Abstract: In this paper, an adaptive trajectory tracking controller for quadrotor MAVs is presented. The controller exploits the common assumption of a faster orientation dynamics w.r.t. the translational one, and is able to asymptotically compensate for parametric uncertainties (e.g., displaced center of mass), as well as external disturbances (e.g., wind). The good performance of the proposed controller is then demonstrated by means of an extensive experimental evaluation performed with a commercially-available quadrotor MAV.

Keywords: Aerial Robotics, Learning and Adaptive Systems, Unmanned Aerial Vehicles
Abstract: Quadrocopters exhibit complex high-speed flight dynamics, and the accurate modeling of these dynamics has proven difficult. Due to the use of simplified models in the design of feedback control algorithms, the execution of high-performance flight maneuvers under pure feedback control typically leads to large tracking errors. This paper investigates an iterative learning scheme aimed at the non-causal compensation of repeatable trajectory tracking errors over the course of multiple executions of periodic maneuvers. The learning is carried out in the frequency domain and uses a simplified model of the closed-loop dynamics of quadrocopter and feedback controller. The resulting algorithm requires little computational power and memory, and its convergence is shown for the nominal model. This paper further introduces a time-scaling method that allows the initial learning to occur at reduced speeds, thus extending the applicability of the algorithm for high performance maneuvers. The presented algorithms are validated in experiments, with a quadrocopter flying a figure-eight maneuver at high speed.

Keywords: Aerial Robotics, Unmanned Aerial Systems, Humanitarian technology for energy, environment and safety
Abstract: The growing need of energy, global warming and recent nuclear power plant accidents have shown that renewable energies need to be developed for tomorrow’s world. Wind energy is generally harvested using wind turbines. Unfortunately, these systems have some drawbacks such as their cost, and the amount of steel and concrete used for construction. As their size grows, their complexity increases exponentially. This paper studies an alternative solution for the production of wind energy, using a kite’s traction force. The aim of this paper is to control the amount of energy produced by the kite, and to be able to fly it safely in the presence of strong wind gusts. Our theoretical work has been implemented in a scale model flying autonomously in a wind tunnel. The proposed control strategy has led to control the system output power with an accuracy greater than 95%, with unknown wind speeds varying from 7.5 to 9 m/s.

Attachments: Video Attachment
Keywords: Dexterous Manipulation, Grasping, Multifingered Hands
Abstract: Replicating human hand capabilities on robotic hands is a great challenge in robotics. The high complexity of mechanical and actuation systems of available robotic device can be, however, considerably mitigated if a human inspired control is considered. In this paper the application of an object- based mapping to the control of robot hands is presented. The basic idea is to use a virtual object, e.g. a virtual sphere, to capture human hand motion generating suitable reference signals for a low level controller of the robotic hand. The low level controller considered, which shares the idea of virtual object to reduce the complexity of the control, is the static Intrinsically Passive Controller (s-IPC). This controller is inspired by the dynamic IPC, but provides a simpler and more efficient implementation. The proposed approach allows to map motion of a human hand model, controlled on the reduced subspace of postural synergies, onto robotic hands guaranteeing the stability of the robotic grasp. This concept, which has been experimentally validated in the paper, can be exploit for complex planning methods or used in telemanipulation application.

Attachments: Video Attachment
Keywords: Dexterous Manipulation, Grasping, Multifingered Hands
Abstract: We propose a feedback-based solution for the accurate manipulation of an unknown object in hand. This method does not explicitly take the friction and surface geometry of the manipulated object into consideration for the controller design, but employs a fast feedback loop based on visual and tactile feedback to perform robust manipulation even in the presence of unexpected slippage or rolling.

At every control step, fingertip motions are computed to realize the intended object relocation, employing a composite position/force controller. Subsequently inverse hand kinematics is employed to retrieve joint-level motions, which are implemented on the robot with a position servo loop.

We evaluate our method on two KUKA robot arms, each equipped with a tactile sensor array as end-effectors to perform the object manipulation task. The experimental results show the feasibility of our proposed method, even in presence of slippage or external disturbances.

Keywords: Dexterous Manipulation, Manipulation Planning and Control, Force Control
Abstract: Force-position control through one or multiple robots, or fingers, typically assumes a rigid endpoint without rolling nor slipping. However, there are some interesting tasks where rolling is involved, such as turning a knob (object is pivoting at a fixed rotational axis) or rolling a wheel (object rotational axis is moving). In such a case, rigid endpoint force control becomes very difficult if not impossible, even for us humans. This stems from two facts, firstly, infinitesimally small rigid point does not yield a tangent force, therefore it is very difficult to control it indirectly; and secondly, the pair robot-object stands for a highly non-linear constrained underactuated dynamical systems. In this paper, we aim at exploring rolling of a rigid dynamic circular object with hemispherical deformable fingertip, then with area, not point, contact. The dynamic model and a control scheme are presented inspired in previous works, but regulation of normal and tangential forces, as well as position and orientation of the object are synthesized. In particular, tangential force control proves instrumental to regulate posture, and displacement of the object with a simple transpose Jacobian Cartesian textit{PDF+g} control. Regulation of rolling angle and displacement with stable normal and tangential exerted forces are obtained without force sensing, neither any model of the deformation nor any dynamic parameter of the object. To entertain these control objectives, a redundant configuration is required so as to yield local regulation, based on the stability-in-the-manifold criteria, whose dimension is greater than the operational space. Illustrative simulations are discussed that provide insight into the closed-loop numerical performance, and finally, remarks on the structure and potential applications are addressed.

Attachments: Video Attachment
Keywords: Dexterous Manipulation, Adaptive Control, Manipulation Planning and Control
Abstract: Handling objects with a single hand without dropping the object is challenging for a robot. A possible way to aid the motion planning is the prediction of the sensory results of different motions. Sequences of different movements can be performed as an offline simulation, and using the predicted sensory results, it can be evaluated whether the desired goal is achieved. In particular, the task in this paper is to roll a sphere between the fingertips of the dexterous hand of the humanoid robot TWENDY-ONE. First, a forward model for the prediction of the touch state resulting from the in-hand manipulation is developed. As it is difficult to create such a model analytically, the model is obtained through machine learning. To get real world training data, a dataglove is used to control the robot in a master-slave way. The learned model was able to accurately predict the course of the touch state while performing successful and unsuccessful in-hand manipulations. In a second step, it is shown that this simulated sequence of sensor states can be used as input for a stability assessment model. This model can accurately predict whether a grasp is stable or whether it results in dropping the object. In a final step, a more powerful grasp stability evaluator is introduced, which works for our task irrespective of the sphere diameter.

Attachments: Video Attachment
Keywords: Dexterous Manipulation, Multifingered Hands, Grasping
Abstract: The present paper introduces a planning and control strategy for whole-arm manipulation of a slippery polygonal object. Randomized planning methods are first proposed in order to generate contact state transitions, which help not only to reduce the amount of calculation required, but also to handle a hybrid system composed of a continuous system and a discrete system, which has a large search space and complicated constraints. Second, a novel control strategy, which can switch manipulation modes among quasi-static, dynamic, and caging manipulation depending on the situation, is proposed. This strategy not only can cope with changes in the mechanics of the system caused by contact state transitions, but also can increase the manipulation feasibility and reliability. The validity of the proposed methods is verified through simulations and experiments.

Keywords: Dexterous Manipulation, Underactuated Robots, Humanoid Robots
Abstract: Recent studies on underactuated manipulation usually describe the system with a Kinematic Model (KM), which is built by adding external constraints to the standard manipulation analysis method. However, such additional constraints are easily violated in a real-world dexterous manipulation task which results in significant control errors. In this work, the Enhanced Kinematic Model (E-KM), an integrated model of the KM and the Sparse Online Gaussian Process (SOGP) is proposed. The E-KM can compensate the shortfalls of the KM by on-the-fly training the SOGP on the residual between the KM and the ground truth data. Based on the E-KM, we further contribute an optimal controller for underactuated manipulations. This optimal E-KM controller is implemented and tested on the iCub, a humanoid robot with two anthropomorphic underactuated hands. Two sets of real-world experiments are carried out to verify our method. The results demonstrate that the E-KM statistically can achieve higher control accuracy than using solely the KM for a wide range of objects.

Attachments: Video Attachment
Keywords: Redundant Robots, Motion Control
Abstract: A kinematically redundant robot with limited motion capabilities, expressed by inequality constraints of the box type on joint variables and commands, needs to perform a set of tasks, expressed by linear equality constraints on robot commands, possibly organized with priorities. Robot motion capabilities cannot be exceeded at any time, and the resulting constraints are to be considered as hard bounds. Instead, robot tasks can be relaxed by velocity scaling if no feasible solution exists. To address this redundancy resolution problem, we developed a method in which joint space commands are successively saturated and their effect compensated in the null space of a suitable task Jacobian (SNS, Saturation in the Null Space). Computationally efficient versions of the basic and optimal SNS algorithms are proposed here, based on a task augmentation reformulation, a QR factorization of the main matrices involved, and a so-called warm start procedure. The obtained performance allows to control in real time robots with high-dimensional configuration spaces executing a large number of prioritized tasks, and with an associated high number of hard bounds that saturate during motion.

Keywords: Kinematics, Industrial Robots, Redundant Robots
Abstract: We propose a robust and fast solution for the inverse kinematic problem of general serial manipulators – i.e. any number and any combination of revolute and prismatic joints. The algorithm only requires the Denavit-Hartenberg (D-H) representation of the robot as input and no training or robot-dependent optimization function is needed. In order to handle singularities and to overcome the possibility of multiple paths in redundant robots, our approach relies on the computation of multiple (parallel) numerical estimations of the inverse Jacobian while it selects the current best path to the desire configuration of the end-effector. But unlike other iterative methods, our method achieves sub-millimeter accuracy in 20.48ms in average. The algorithm was implemented in C/C++ using 16 POSIX threads, and it can be easily expanded to use more threads and/or many-core GPUs. We demonstrate the high accuracy and the real-time performance of our method by testing it with five different robots, at both non-singular and singular configurations, including a 7-DoF redundant robot.

Attachments: Video Attachment
Keywords: Kinematics, Sensor Fusion, Motion Control
Abstract: We consider full motion state sensing of a rigid open-chain multi-body linkage assembly using rate gyros and linear accelerometers. The research is built upon micro-electro-mechanical systems (MEMS) components for low-cost ``strap-down'' implementation. Our emphasis is on direct lag-free joint angular acceleration sensing, for which a novel multi-MEMS configuration is motivated by motion control requirements. By using the multi-MEMS configuration, the bandwidth of the angular acceleration sensed is mostly proportional to the physical distances of linear accelerometers. The related joint position sensing, which is robust against linear and angular motion, is founded on the complementary and Kalman filtering principles for exclusive low delay. Experiments on a robotic vertically mounted three-link planar arm demonstrate the advantage of our key theoretical finding.

Keywords: Industrial Robots, Integrated Planning and Control, Motion Control
Abstract: We consider planning and implementation of fast motions for industrial manipulators constrained to a given geometric path. With such a problem formulation, which is quite reasonable for many standard operation scenarios, it is intuitively clear that a feedback controller should be designed to achieve orbital stabilization of a time-optimal trajectory instead of asymptotic one. We propose an algorithm to convert an asymptotically stabilizing controller into an orbitally stabilizing one and check achievable performance in simulations and, more importantly, in experiments performed on a standard industrial robot ABB IRB 140 with the IRC5-system extended with an open control interface. It is verified that the proposed re-design allows significantly reducing deviations of the actual trajectories from the desired one at high speeds not only for a chosen base feedback design but also outperforming the state-of-the art commercial implementation offered by ABB Robotics.

Keywords: Underactuated Robots, Dynamics, Intelligent Toys
Abstract: We analyze the problem of dynamic nonprehensile manipulation by considering the example of the butterfly robot. Our main objective is to study the problem of stabilizing periodic motions, which resemble some form of juggling acrobatics. To this end, we approach the problem by considering the framework of virtual holonomic constraints. Under this basis, we provide an analytical and systematic solution to the problems of trajectory planning and design of feedback controllers to guarantee orbital exponential stability. Results are presented in the form of simulation tests.

Keywords: Motion and Trajectory Generation, Aerial Robotics
Abstract: This paper presents missile guidance as a complex robotic problem: a hybrid non-linear system moving in a heterogeneous environment. The proposed solution to this problem combines a sampling-based path planner, Dubins’ curves and a locally-optimal guidance law. This algorithm aims to find feasible trajectories that anticipate future flight conditions, especially the loss of manoeuverability at high altitude. Simulated results demonstrate the substantial performance improvements over classical midcourse guidance laws and the benefits of using such methods, well-known in robotics, in the missile guidance field of research.

Keywords: Computer-assisted diagnosis and therapy, Force and Tactile Sensing, Medical Robots and Systems
Abstract: This paper presents a novel fiber optic tactile probe designed for tissue palpation during minimally invasive surgery (MIS). The probe consists of 3×4 tactile sensing elements at 2.6mm spacing with a dimension of 12×18×8 mm3 allowing its application via a 25mm surgical port. Each tactile element converts the applied pressure values into a circular image pattern. The image patterns of all the sensing elements are captured by a camera attached at the proximal end of the sensor system. Processing the intensity and the area of these circular patterns allows the computation of the applied pressure across the sensing array. Validation tests show that each sensing element of the tactile probe can measure forces from 0 to 1N with a resolution of 0.05 N. The proposed sensing concept is low cost, lightweight, sterilizable, easy to be miniaturized and compatible for magnetic resonance (MR) environments. Experiments using the developed sensor for tissue abnormality detection were conducted. Results show that the proposed tactile probe can accurately and effectively detect nodules embedded inside soft tissue, demonstrating the promising application of this probe for surgical palpation during MIS.

Attachments: Video Attachment
Keywords: Medical Robots and Systems, Surgical Robotics, Tendon/Wire Mechanism
Abstract: Flexible minimally invasive surgical instruments can be used to target difficult-to-reach locations within the human body. Accurately steering these instruments requires information about the three-dimensional shape of the instrument. In the current study, we use an array of Fiber Bragg Grating (FBG) sensors to reconstruct the shape of a flexible instrument. FBG sensors have several advantages over existing imaging modalities, which makes them well-suited for use in a clinical environment. An experimental testbed is presented in this study, which includes a tendon-driven manipulator. A nitinol FBG-wire is fabricated, on which an array of twelve FBG sensors are integrated, and distributed over four different sets. This wire is positioned in the backbone of the manipulator. Axial strains are measured using the FBG sensors, from which the curvature of the manipulator is calculated. The three-dimensional manipulator shape is reconstructed from the curvature, which is used to steer the manipulator tip. We are able to steer the manipulator along various trajectories (two-dimensional and three-dimensional), and also reject disturbance loads. We observe a minimum mean tracking error of 0.67 mm for the circular trajectory in closed-loop control. This study demonstrates the potential of steering flexible minimally invasive surgical instruments using an array of FBG sensors.

Keywords: Medical Robots and Systems, Surgical Robotics, Force and Tactile Sensing
Abstract: The small scale of minimally-invasive surgery (MIS) presents significant challenges to developing robust, smart, and dexterous tools for manipulating millimeter and sub-millimeter anatomical structures (vessels, nerves) and surgical equipment (sutures, staples). Robotic MIS systems offer the potential to transform this medical field by enabling precise repair of these miniature tissue structures through the use of teleoperation and haptic feedback. However, this effort is currently limited by the inability to make robust and accurate MIS end effectors with integrated force and contact sensing. In this paper, we demonstrate the use of the novel Pop-Up Book MEMS manufacturing method to fabricate the mechanical and sensing elements of an instrumented MIS grasper. A custom thin-foil strain gage was manufactured in parallel with the mechanical components of the grasper to realize a fully-integrated electromechanical system in a single manufacturing step, removing the need for manual assembly, bonding and alignment. In preliminary experiments, the integrated grasper is capable of resolving forces as low as 30 mN, with a sensitivity of approximately 408 mV/N. This level of performance will enable robotic surgical systems that can handle delicate tissue structures and perform dexterous procedures through the use of haptic feedback guidance.

Keywords: Surgical Robotics, Medical Robots and Systems, Haptics and Haptic Interfaces
Abstract: This paper presents an ungrounded, hand-held surgical device that incorporates active constraints and force-feedback. Optical tracking of the device and embedded actuation allow for real-time motion compensation of a surgical tool as an active constraint is encountered. The active constraints can be made soft, so that the surgical tool tip motion is scaled, or rigid, so as to altogether prevent the penetration of the active constraint. Force-feedback is also provided to the operator so as to indicate penetration of the active constraint boundary by the surgical tool. The device has been evaluated in detailed bench tests to quantify its motion scaling and force-feedback capabilities. The combined effects of force-feedback and motion compensation are demonstrated during palpation of an active constraint with rigid and soft boundaries. A user study evaluated the combined effect of motion compensation and force-feedback in preventing penetration of a rigid active constraint. The results have shown the potential of the device operating in an ungrounded setup that incorporates active constraints with force-feedback.

Keywords: Medical Robots and Systems
Abstract: As a preliminary step to achieve a long-term goal of developing an automatic dental preparation system for clinical operations, we design and build a miniature robotic system which can manipulate a laser beam to move in three dimensional spaces to remove hard tissue from a target tooth. The dental preparation requires the robotic system to own high accuracy, high ablation speed and small size. A 2D galvanometer scanners module is integrated to meet the requirement of a high moving speed of the laser focus. A closed-loop system based on a miniature-sized voice-coil motor and a grating ruler are developed to realize the accurate control of the focus. The overall size of the developed prototype is 108mm×56mm×43mm, which is small enough to be used in close proximity to a patient's mouth. The prototype has been tested by using two different kinds of laser generators, i.e.，a nanosecond laser and a picosecond laser. The experiment results show that the robotic system can provide high moving speed of 1000mm/s with good shape accuracy. From the results, we found that nanosecond laser beam can be controlled to ablate zirconia and aluminum, but not suitable to ablate tooth because of tissue carbonization. By selecting suitable parameters of the picosecond laser generator, a target tooth could be ablated to produce a cylinder shape without carbonization. Limitations of the prototype are identified according to the experiment results.

Attachments: Video Attachment
Keywords: Surgical Robotics, Robot Safety, Learning from Demonstration
Abstract: Loss of haptic sensation in a master-slave system is one of the open problems in robotic surgery, and recognition of surgical situations through haptic sensation is a challenge. In this paper we propose an autonomous risk-detection system for a master-slave surgical robotic system in order to estimate a property of an object (i.e., contact impedance) using a force sensor mounted on a surgical robotic instrument. The system autonomously detects the risk based on the estimated contact impedance and accordingly activates the motion at the slave unit as well as the force feedback at the master unit. We implemented the proposed method in a teleoperated master-slave system to detect the perforation risk of a membranous object. The performance of the system was evaluated through experiments. The classification accuracy for perforation risk was about 98.5 % in fourfold cross-validation. The experiments verified that the risk detection system accurately detected the perforation risk and improved the safety of the master-slave system.

Attachments: Video Attachment
Keywords: Humanoid Robots, Dynamics, Underactuated Robots
Abstract: Simple inverted pendulum models and their variants are often used to control humanoid robots in order to simplify the control design process. These simple models have significantly fewer degrees of freedom than the full robot model. The design and choice of these simple models are based on the designer's intuition, and the reduced state mapping and the control input mapping are manually chosen. This paper presents an automatic model reduction procedure for humanoid robots, which is task-specific. It also presents an optimization framework that uses the auto-generated task-specific reduced models to control humanoid robots. Successful simulation results of balancing, fast arm swing, and hip rock and roll motion tasks are demonstrated.

Keywords: Humanoid Robots, Computer Vision, Perception for Grasping and Manipulation
Abstract: Humanoid robots should be able to visually recognize objects and estimate their 6D pose in real environmental conditions with their limited sensor capabilities. In order to achieve these visual skills, it is necessary to establish an optimal visual transducer connecting the scene layout with the internal representations of objects and places. This visual transducer should capture the noiseless visual manifold of the scene with high-dynamic-range in an efficient manner. Our endeavor is to develop such a visual transducer using the widespread LDR cameras in humanoid robots. In our previous work, the noiseless acquisition of continuous images [1] and the improved radiometric calibration [2] already enabled the humanoid robots to attain the desired visual manifold in terms of quality. However, since the radiance range of the scene can be very wide, the required amount of exposures to capture the visual manifold (robustly without radiance inconsistencies) turns impractically large in terms of scope, granularity and acquisition time. In this article, a method for estimating the minimal amount of exposures and their particular integration times is presented. This method integrates our previous work in order to synthesize HDR images with the minimal amount of exposures while ensuring the high quality of the resulting image. Conclusively, the minimal exposure set provides performance improvements without quality trade-off. Experimental evaluation is presented with the humanoid robots ARMAR-{IIIa,b} [3].

Keywords: Robot Safety, Humanoid Robots, Humanoid and Bipedal Locomotion
Abstract: We present a semi-supervised anomaly detection system for humanoid robots that operates on trajectories with varying lengths, resolutions, and time shifts. The proposed approach utilities optimization to extract a model from joint trajectories under normal operation and seek to identify anomalous behaviors that deviates significantly from the known model. Compared to previously proposed approaches in humanoid anomaly detection that identified only high-level faults, our approach can detect subtle defects in the robot and at the same time, is capable of generalizing to higher-level behaviors. The system is demonstrated on a simulated model of the Atlas humanoid robot, with several experimental scenarios demonstrating detection of both joint-level anomalies and behaviors such as falling.

Attachments: Video Attachment
Keywords: Humanoid and Bipedal Locomotion, Underactuated Robots, Force Control
Abstract: In this paper, we extend the Divergent Component of Motion (DCM, also called 'Capture Point') to 3D. We introduce the "Enhanced Centroidal Moment Pivot point" (eCMP) and the "Virtual Repellent Point" (VRP), which allow for the encoding of both direction and magnitude of the external (e.g. leg) forces and the total force (i.e. external forces plus gravity) acting on the robot. Based on eCMP, VRP and DCM, we present a method for real-time planning and control of DCM trajectories in 3D. We address the problem of underactuation and propose methods to guarantee feasibility of the finally commanded forces. The capabilities of the proposed control framework are verified in simulations.

Attachments: Video Attachment
Keywords: Humanoid Robots
Abstract: In the case of object manipulation by a humanoid robot, it is important to deal with contact states between objects, a robot, and an environment both to avoid falling down and to achieve objective manipulations. We propose a method to describe and uniformly execute various object manipulations by a humanoid robot. In description, we focus on the contact states and define manipulation phases according to the contact states. In execution, the humanoid's controller autonomously switches manipulation phases and substantiates the contact-force controller. According to switching of the manipulation phases, the humanoid's manipulation system switches the inputs for the contact-force controller, which includes the estimation of object's information and motion generation. We evaluated our proposed system through experiments in which the HRP-2 robot manipulates four objects without information about the objects' masses and necessary operational forces.

Attachments: Video Attachment
Keywords: Legged Robots, Learning and Adaptive Systems, Biomimetics
Abstract: This paper shows improvement of stability and efficiency for mobility using locomotion selection strategy. First strategy is the selection of a gait relying on locomotion rewards. The locomotion reward has been proposed as an indicator for selection algorithm based on Falling Risk and the moving speed. This strategy has achieved a capability of large changes of uncertainties, such as a steep slope. Second strategy is adjustment of moving speed by the extended locomotion reward that explicitly shows the relationship between the moving speed and Falling Risk. The robot aims at the maximum moving speed without a falling, and removes small changes of uncertainties as a result. We performed an experiment in order to confirm effects of two strategies in an environment that includes a rough terrain as a small uncertainty and two steps as a large uncertainty. The robot improved the moving speed about 37.5% from the case of only using the gait selection strategy.

Attachments: Video Attachment
Keywords: Navigation, Swarm Robotics, Agent-Based Systems
Abstract: Most local robot navigation algorithms are based on the concept of velocity obstacle, a mechanistic approach to the navigation problem in which a solution is engineered from scratch. Over the years, a number of different velocity obstacle variants have been developed to effectively handle multi-robot systems. In parallel, an alternative, human-inspired approach for robot navigation has been recently proposed, which derives from the observation and modeling of crowds of pedestrians.

We discuss similarities and differences among two broadly used obstacle-velocity variants, namely Hybrid Reciprocal Velocity Obstacle and Optimal Reciprocal Collision Avoidance, and the human-inspired approach. How do these differences (which are often subtle) impact performance, and why? We answer these questions through extensive simulation experiments, wherein we evaluate the the algorithms for safety, trajectory efficiency, and emergence of collective behaviors, in different challenging multi-robot scenarios using both ideal and realistic models for robots and sensing.

Attachments: Video Attachment
Keywords: Navigation, Mapping, Autonomous Agents
Abstract: We propose Bayesian approaches for semantic mapping, active localization and local navigation with affordable vision sensors. We develop Bayesian model of egocentric semantic map which consists of spatial object relationships and spatial node relationships. Our topological-semantic-metric (TSM) map has characteristic that a node is one of the components of a general topological map that contains information about spatial relationships. In localization part, view dependent place recognition, reorientation and active search are used for robot localization. A robot estimates its location by Bayesian filtering which leverages spatial relationships among observed objects. Then a robot can infer the head direction to reach a goal in the semantic map. In navigation part, a robot perceives navigable space with Kinect sensor and then moves to goal location while preserving reference head direction. If obstacles are founded in front, then a robot changes the head direction to avoid them. After avoiding obstacles, a robot performs active localization and finds new head direction to goal location. Our Bayesian navigation program provides how a robot should select either an action for following line of moving direction or action for avoiding obstacles. We show that a mobile robot successfully navigates from starting position to goal node while avoiding obstacles by our proposed semantic navigation system with TSM map.

Attachments: Video Attachment
Keywords: Navigation, Localization, Mapping
Abstract: Precise navigation is a key capability of autonomous mobile robots and required for many tasks including transportation or docking. To guarantee a robust and accurate localization and navigation performance, many practical approaches rely on observations of artificial landmarks. This raises the question of where to place the landmarks along the desired trajectory of the robot. In this paper, we present a novel approach to landmark selection, which aims at selecting the minimal set of landmarks that bounds the uncertainty about the deviation of the robot from its desired trajectory. At the same time the selected landmark sets are robust against the fact that a certain number of landmarks can be obscured from view during operation. Our algorithm is highly efficient due to a linearization of the whole navigation cycle and employs submodular optimization, for which strong formal bounds on the approximation quality are known. In extensive experiments, also carried out with a real robot, we demonstrate that our approach outperforms several other methods and that it enables robust autonomous robot navigation in practice.

Keywords: Navigation, Motion and Path Planning, Integrated Planning and Control
Abstract: Platforms with holonomic drives are particularly interesting due to their maneuvering capabilities. Robots used for transportation tasks usually have a non-circular footprint. In this work, we present a navigation strategy for a holonomic mobile robot with anyshape footprint. Our technique introduces an efficient navigation method based on a strategy that makes use of discrete and continuous techniques. We introduce compact discrete intervals to represent the free space for computing fast-to-update plans. Based on these, we provide a continuous motion generation approach to generate smooth motions that are fast to compute. We evaluated our approach by running simulated experiments and by using a real holonomic L-shaped robot. Our experiments demonstrate that our technique can be carried out online and is able to smoothly drive the robot to its goal locations even in dynamic environments.

Keywords: Localization, Multi-Robot Coordination, Marine Robotics
Abstract: We report the first experimental results of the navigation method of multiple Autonomous Underwater Vehicles (AUVs) for wide seafloor surveys proposed by us in our previous reports. The key idea of the proposed method is that moving AUVs estimate their states (horizontal position and heading angle) based on AUVs remaining stationary on the seafloor (landmark AUVs), alternating between these roles to expand the observational coverage. Moving AUVs land on the seafloor and transmit compressed information about their estimated states to the landmark AUVs when they change the roles. Sea trials were carried out using two AUVs to evaluate the performance of this method. One is the AUV Tri-Dog 1 (TD) which can move and estimate the states and the other is a Dummy AUV (DA) which cannot move but can estimate the states. In the experiments, TD and DA alternatively estimated the states. To evaluate the positioning accuracy of the proposed method, the states were recalculated based on sensor data obtained at sea trials in post processing. As a result, positioning errors of the proposed method were estimated to be smaller than dead reckoning. The Errors were found to be about 0.4 m in horizontal position and about 1.5 degree in heading angle. The method demonstrated to be successful in stable positioning with AUVs alternating between the moving role and the landmark role. Future works include the verification of the method using two AUVs in sea environment to realize wide seafloor survey.

Attachments: Video Attachment
Keywords: Humanoid Robots
Abstract: In this paper, we present an integrated navigation system that allows humanoid robots to autonomously navigate in unknown, cluttered environments.From the data of an on-board consumer-grade depth camera, our system estimates the robot's pose to compensate for drift of odometry and maintains a heightmap representation of the environment.Based on this model, our system iteratively computes sequences of safe actions including footsteps and whole-body motions, leading the robot to target locations. Hereby, the planner chooses from a set of actions that consists of planar footsteps, step-over actions, as well as parameterized step-onto and step-down actions.To efficiently check for collisions during planning, we developed a new approach that takes into account the shape of the robot and the obstacles.As we demonstrate in experiments with a Nao humanoid, our system leads to robust navigation in cluttered environments and the robot is able to traverse highly challenging passages.

Attachments: Video Attachment
Keywords: Visual Tracking, Computer Vision, Visual Navigation
Abstract: We conducted high-frame-rate (HFR) video mosaicing for real-time synthesis of a panoramic image by implementing an improved feature-based video mosaicing algorithm on a field-programmable gate array (FPGA)-based high-speed vision platform. In the implementation of the mosaicing algorithm, feature point extraction was accelerated by implementing a parallel processing circuit module for Harris corner detection in the FPGA on the high-speed vision platform. Feature point correspondence matching can be executed for hundreds of selected feature points in the current frame by searching those in the previous frame in their neighbor ranges, assuming that frame-to-frame image displacement becomes considerably smaller in HFR vision. The system we developed can mosaic 512x512 images at 500 fps as a single synthesized image in real time by stitching the images based on their estimated frame-to-frame changes in displacement and orientation. The results of an experiment conducted, in which an outdoor scene was captured using a hand-held camera-head that was quickly moved by hand, verify the performance of our system.

Keywords: Visual Tracking
Abstract: We have developed a fast target tracking system that utilizes four cameras with lenses of different focal lengths to track an object without blurring images, even when the object moves in the depth direction away from the cameras in three-dimensional (3-D) space. This system can maintain a well-focused camera view by switching among the four input images, instead of using lens motor control. The multi-camera system was mounted on a two-axis mechanical active vision platform. The active vision control and camera-view switching are executed by processing color 512x512 images from the four camera inputs at 500 fps in real time on a high-speed vision platform. The performance of our system was verified by its tracking results for objects moving rapidly in 3-D space.

Attachments: Video Attachment
Keywords: Micro/Nano Robots, Visual Servoing, Nano manipilation
Abstract: Fast and reliable autofocusing methods are essential for performing automatic nano-objects positioning tasks using a scanning electron microscope (SEM). So far in the literature, various autofocusing algorithms have been proposed utilizing a sharpness measure to compute the best focus. Most of them are based on iterative search approaches; applying the sharpness function over the total range of focus to find an image in-focus. In this paper, a new, fast and direct method of autofocusing has been presented based on the idea of traditional visual servoing to control the focus step using an adaptive gain. The visual control law is validated using a normalized variance sharpness function. The obtained experimental results demonstrate the performance of the proposed autofocusing method in terms of accuracy, speed and robustness.

Attachments: Video Attachment
Keywords: Computer Vision, Visual Tracking, Visual Servoing
Abstract: We propose a novel dot-pattern-projection three-dimensional (3-D) shape measurement method that can measure 3-D displacements of blink dots projected onto a measured object accurately even when it moves rapidly or is observed from a camera as moving rapidly. In our method, blinking dot patterns, in which each dot changes its size at different timings corresponding to its identification number, are projected from a projector at a high frame rate. 3-D shapes can be obtained without any miscorrespondence of the projected dots between frames by simultaneous tracking and identification of multiple dots projected onto a measured 3-D object in a camera view. Our method is implemented on a field-programmable gate array (FPGA)-based high-frame-rate (HFR) vision platform that can track and recognize as much as 15x15 blink-dot pattern in a 512x512 image in real time at 1000 fps, synchronized with an HFR projector. We demonstrate the performance of our system by showing real-time 3-D measurement results when our system is mounted on a parallel link manipulator as a sensing head.

Attachments: Video Attachment
Keywords: Biologically-Inspired Robots, Computer Vision, Cellular and Modular Robots
Abstract: This paper presents a new dynamics-based method for image processing in coordination with rapid ocular movement. A camera positioning mechanism with piezoelectric cellular actuators will be employed to demonstrate the effectiveness of this approach. There are a number of mechanisms for automatic camera positioning, but few have much in common with the human ocular positioning system. When a rapid point-to-point motion is created in a camera positioner, like human saccadic motion, the image sensor receives blurry images. Existing image techniques rely solely on obtained images, or use external sensors to estimate a blur kernel, or point spread function (PSF), for motion deblurring. Inspired by recent oculomotor studies, this paper proposes a method for estimating PSFs directly from the system dynamics of a camera positioning mechanism without motion sensors. The proposed method has been evaluated by using a single degree-of-freedom camera orientation system. Results are compared with conventional methods in terms of speed and accuracy.

Keywords: Computer Vision, SLAM, Sensor Fusion
Abstract: While inexpensive depth sensors are becoming increasingly ubiquitous, field of view and self-occlusion constraints limit the information a single sensor can provide. For many applications one may instead require a network of depth sensors, registered to a common world frame and synchronized in time. Historically such a setup has required a tedious manual calibration process, making it infeasible to deploy these networks in the wild, where spatial and temporal drift are common. In this work, we propose an entirely unsupervised process for calibrating the relative pose and time offsets of a pair of depth sensors. So doing, we make no use of an explicit calibration target, or any intentional activity on the part of a user. Rather, we use the unstructured motion of objects in the scene to find potential correspondences between the sensor pair. This yields a rough transform which is then refined with an occlusion-aware energy minimization. We compare our results against the standard checkerboard technique, and provide qualitative examples for scenes in which such a technique would be impossible.

Keywords: Service Robots, Cognitive Human-Robot Interaction, Domestic Robots and Home Automation
Abstract: In spite of IT innovation, people cannot get rid of non-creative tasks of searching daily-use objects at home. This paper presents a drawer-type storage system for supporting object search, ”TansuBot”. By using this system and a smart device (e.g. smart phone), a user can review the photos of contents stored in the system. In addition, the system can present candidate drawers where the searching target object may be stored based on preliminary information such as usage histories. Concretely, LED blinking and pop-up actions (pushing drawers forward) are used for display. To realize these supports, a stacker crane type wall-moving robot is equipped at the backside of storage. The robot has a movable camera and mechanisms to push a drawer forward. For easy installation to a home, storage efficiency and cost reduction should be considered in the design of the instrument. Especially for cost reduction, this paper presents an approach to use wooden parts for main mechanisms. This approach also contributes to user-friendly presence and appearance of the instrument. This paper reports about the development of a prototype and an experiment to evaluate the functions for supporting object search. The results of the experiment prove the importance of the functions realized by the system; displaying contents’ photos on a smart device and showing candidate drawers to investigate. The outcomes indicate that those functions have positive effects on reduction of searching time and mental burden.

Keywords: Service Robots, Industrial Robots, Computer Vision
Abstract: This paper describes about a method of clothing classification using a single image. The method assumes to be used for building autonomous systems, with the purpose of recognizing day-to-day clothing thrown casually. A set of Gabor filters is applied to an input image, and then several image features that are invariant to translation, rotation and scale are generated. In this paper, we propose the descriptions of the features with focusing on clothing fabrics, wrinkles and cloth overlaps. Experiments of state description and classification using real clothing show the effectiveness of the proposed method.

Keywords: Domestic Robots and Home Automation, Adaptive Control, Human Centered Automation
Abstract: Air conditioning systems are generally the largest systems in a home, both physically and energetically, and thus central to home automation efforts. Finding a balance between user comfort and efficiency is a complex problem given the considerable variation present. This paper focuses on comfort, as opposed to absolute temperature, as gauged using simple, sparse user inputs. A thermal model of the house is learned which accounts for weather data and exogenous factors such as occupancy. By incorporating user feedback, a Learning-Based Model Predictive Controller (LBMPC) is able adapt to home conditions and more efficiently operate the system. In contrast to previous efforts which operate in office spaces and to a set point, this work is adapted and tested in a typical home environment and closes a control loop on user comfort. The controller considers that the user's comfort levels may change during the day, for example when the user is in bed, or not at home. It shows that complex systems may be automated without extensive tweaking by the user and in a manner that considers user comfort, time of day, and related factors to reduce energy consumption.

Keywords: Service Robots, Wheeled Robots
Abstract: This paper designs an innovative prediction-based interception control strategy to enable a wheeled mobile robot to intercept a dynamic target with a specified angle, which can be potentially utilized in such applications as service robots. Specifically, visual information is collected and then utilized to estimate the state of the moving target, based on which, the follow-up pose of the target is calculated so as to improve the interception accuracy. A prediction-based controller is then proposed to drive the wheeled robot to efficiently intercept a dynamic target with a specified angle, whose stability is proven by Lyapunov techniques. Both simulation and experimental results are provided to demonstrate the superior performance of the proposed approach.

Keywords: Domestic Robots and Home Automation, Wheeled Robots, Climbing robots
Abstract: In this paper, an automatic erect stair climbing mobile robot is developed for indoor service applications. The design of high center of mass, tilt axis near ground, and the triangular wheel-legged structure enable the robot to climb stairs in a dynamic and self-balancing way. The wheel-legged mechanism also keep the advantages of differential-wheeled mobile platforms when moving on flat ground, such as easy to control, saving power, and zero turning radius. Moreover, the overall mechanical design fits the requirements for a service robot to have proper height and small footprint, which can make human-robot interaction more natural and comfortable in indoor environment. Since the perceptual and control system of the robot are both well integrated, we successfully demonstrate the stair-climbing function and prove that the design and implementation of our work are feasible and efficient. As a result, the robot is expected to be a prototype of universal platform for indoor mobile service robots in the future.

Keywords: Human Centered Planning and Control, Robot Companions and Social Human-Robot Interaction, Human-Robot Interaction
Abstract: Reliable autonomous navigation is an active research topic that has drawn the attention for decades, however, human factors such as navigational comfort has not received the same level of attention. This work proposes the concept of “comfortable map” and presents a navigation approach for autonomous passenger vehicles which in top of being safe and reliable is comfortable. In our approach we first extract information from users preference related to comfort while sitting on a robotic wheelchair under different conditions in an indoor corridor environment. Human-comfort factors are integrated to a geometric map generated by SLAM framework. Then a global planner computes a safe and comfortable path which is followed by the robotic wheelchair. Finally, an evaluation with 29 participants using a fully autonomous robotic wheelchair, showed that more than 90% of them found the proposed approach more comfortable than a shortest-path state of the art approach.

Keywords: Recognition, Intelligent Transportation Systems, Sensor Fusion
Abstract: Time-series driving behavioral data and image sequences captured with car-mounted video cameras can be annotated intuitively in natural language, for example, ``in a traffic jam,'' ``leading vehicle is a truck,'' or ``there are three and more lanes.'' Various driving support systems nowadays have been developed for safe and comfortable driving. To develop more effective driver assistance systems, namely, to achieve fully cooperative driving between a human driver and vehicle, abstractive recognition of driving situation performed just like the driver is important. To achieve human-like annotation of driving behavioral data and image sequences, we first divided continuous driving behavioral data into discrete symbols that represent driving situations. Then, using multimodal latent Dirichlet allocation, latent drive topics laid on each driving situation were estimated as a relation model among driving behavioral data, image sequences, and human-annotated tags. Finally, automatic annotation of the behavioral data and image sequences can be achieved by calculating the predictive distribution of the annotations via estimated latent-drive topics. The proposed method intuitively annotated more than 50,000 pieces of frame data, including urban road and expressway data. The effectiveness of the estimated drive topics was also evaluated by analyzing the performances of driving-situation classification. The topics represented the drive context efficiently, i.e., the drive topics lead to a 95% lower-dimensional feature space and 6% higher accuracy compared with a high-dimensional raw-feature space. Moreover, the drive topics achieved performance almost equivalent performance to human annotators, especially in classifying traffic jams and the number of lanes.

Keywords: Recognition, Unmanned Aerial Systems
Abstract: Monitoring and estimation of marine populations is of paramount importance for the conservation and management of sea species. Regular surveys are used to this purpose followed often by a manual counting process. This paper proposes an algorithm for automatic detection of dugongs from imagery taken in aerial surveys. Our algorithm exploits the fact that dugongs are rare in most images, therefore we determine regions of interest partially based on color rarity. This simple observation makes the system robust to changes in illumination. We also show that by applying the extended-maxima transform on red-ratio images, submerged dugongs with very fuzzy edges can be detected. Performance figures obtained here are promising in terms of degree of confidence in the detection of marine species, but more importantly our approach represents a significant step in automating this type of surveys.

Keywords: Recognition, Computer Vision, Learning and Adaptive Systems
Abstract: Machine perception often requires a large amount of user-annotated data which is painful or expensive to collect. Perception systems should be easy to train by regular users, and this is currently far from the case.

Our previous work, tracking-based semi-supervised learning cite{teichman2012b}, helped reduce this burden by using tracking information to harvest new and useful training examples. However, cite{teichman2012b} was designed for offline use; it assumed a fixed amount of unlabeled data and did not allow for corrections from users. In many practical robot perception scenarios we A) desire continuous learning over a long period of time, B) have an infinite stream of unlabeled sensor data available, and C) are willing to periodically provide a small number of new training examples.

In light of this, we present group induction, a new mathematical framework that rigorously encodes the intuition of cite{teichman2012b} in an alternating optimization problem similar to expectation maximization (EM), but with the assumption that the unlabeled data comes in groups of instances that share the same hidden label. This optimization problem suggests several improvements to the original heuristic algorithm and shows how to adapt it to benefit from user interaction and infinite streams of unlabeled data. We evaluate group induction on a track classification task from natural street scenes, demonstrating its ability to learn continuously, adapt to user feedback, and accurately recognize objects of interest.

Keywords: AI Reasoning Methods
Abstract: We introduce a probabilistic language and a fast inference algorithm for state estimation in hybrid dynamic relational domains with an unknown number of objects. More specifically, we apply Particle Filters to distributional clauses. The particles represent (partial) interpretations of possible worlds (with discrete and/or continuous variables) and the filter recursively updates its beliefs about the current state. We use backward reasoning to determine which facts should be included in the partial interpretations. Experiments show that our framework can outperform the classical particle filter and is promising for robotics applications.

Keywords: Recognition, Range Sensing, Perception for Grasping and Manipulation
Abstract: Object detection is here considered as the problem of retrieving from scene data segments that belong to objects from the sought category. The method proposed and investigated works with dense range data, as can be acquired with low-cost sensors. It does not require any training, but just a single geometric prototype that may be taken from an internet repository. Experiments with various household and office scenes are reported, and the performance is quantified on a public dataset. One of the tested variants achieves an F-score and average precision of 94% at total recall, and a correct nearest-neighbor rate of 97%.

Keywords: Localization, Visual Learning, Computer Vision
Abstract: Visual localization in crowded dynamic environments requires information about static and dynamic objects. This paper presents a robust method that learns the useful features from multiple runs in highly crowded urban environments. Useful features are identified as distinctive ones that are also reliable to extract in diverse imaging conditions. Relative importance of features is used to derive the weight for each feature. The popular Bag-of-words model is used for image retrieval and localization, where query image is the current view of the environment and database contains the visual experience from previous runs. Based on the reliability, features are augmented and eliminated over runs. This reduces the size of representation, and makes it more reliable in crowded scenes. We tested the proposed method on data sets collected from highly crowded Indian urban outdoor settings. Experiments have shown that with the help of a small subset (10%) of the detected features, we can reliably localize the camera. We achieve superior results in terms of localization accuracy even when more than 90% of the pixels are occluded or dynamic.

Keywords: Visual Learning
Abstract: It is challenging for a robot acting in the world to interact with and use novel objects. While a person may be able to look past visual differences and recognize the intended function of an object, doing so is more difficult for robots, which tend to rely on visual similarity to recognize categories of objects. A robot that recognizes and classifies objects based on their functional properties and potential capabilities is better prepared to use unknown objects.

We propose a technique for functionally classifying objects using features obtained through physical simulations. The described method simulates spheres falling onto an object from above. We show how a feature vector can be derived from the results of the physics-based simulation, and that this feature vector is informative for a variety of affordance classification tasks. This process allows a robot equipped with a 3D sensor to determine the functionality of objects in its environment given only a few training examples from various function classes. We show that this method is able to accurately learn membership of 3D models in three function classes: "drinking vessel", "table", and "sittable". We then show that this can be extended to 3D scans of objects using the models as training examples.

Keywords: Visual Learning, Perception for Grasping and Manipulation, Learning and Adaptive Systems
Abstract: When it comes to learning how to manipulate objects from experience with minimal prior knowledge, robots encounter significant challenges. When the objects are unknown to the robot, the lack of prior object models demands a robust feature descriptor such that the robot can reliably compare objects and the effects of their manipulation. In this paper, using an experimental platform that gathers 3-D data from the Kinect RGB-D sensor, as well as push action trajectories from a tracking system, we address these issues using an action-grounded 3-D feature descriptor. Rather than using pose-invariant visual features, as is often the case with object recognition, we ground the features of objects with respect to their manipulation, that is, by using shape features that describe the surface of an object relative to the push contact point and direction. Using this setup, object push affordance learning trials are performed by a human and both pre-push and post-push object features are gathered, as well as push action trajectories. A self-supervised multi-view online learning algorithm is employed to bootstrap both the discovery of affordance classes in the post-push view, as well as a discriminative model for predicting them in the pre-push view. Experimental results demonstrate the effectiveness of self-supervised class discovery, class prediction and feature relevance determination on a collection of unknown objects.

Keywords: Learning and Adaptive Systems, Perception for Grasping and Manipulation, Human and humanoid skills/cognition/interaction
Abstract: Understanding and representing objects and their function is a challenging task. Objects we manipulate in our daily activities can be described and categorized in various ways according to their properties or affordances, depending also on our perception of those. In this work, we are interested in representing the knowledge acquired through interaction with objects, describing these in terms of action-effect relations, i.e. sensorimotor contingencies, rather than static shape or appearance representations. We demonstrate how a robot learns sensorimotor contingencies through pushing using a probabilistic model. We show how functional categories can be discovered and how entropy-based action selection can improve object classification.

Keywords: Learning and Adaptive Systems, Range Sensing, Recognition
Abstract: Simultaneous place classification and object detection (SPCOD) is an algorithm which is able to categorize the environment (place) and detect the objects presented in the environment. Although both place classification and object detection problems have been in discussion in literature, as a concept SPCOD is still in its early stage of research. Focusing mainly on the discrimination ability of SPCOD, in this paper we have proposed a pairwise conditional random field (CRF) framework to integrate mature techniques on laser data based place classification and vision based off-the-shelf object descriptor. Extensive experimental results on a public data set demonstrate the effectiveness of the proposed method.

Attachments: Video Attachment
Keywords: Learning and Adaptive Systems, Sensor Fusion, Failure Detection and Recovery
Abstract: A major problem for the application of sensorimotor approaches to robot control is the classification of states. The typically immense sizes of sensorimotor state spaces render it very unlikely that exactly the same states are visited by the robot several times. In order to learn about the consequences of alternative behaviors in these states, a classification of similar or related states is necessary. This requires a metric to measure similarity between states.

Under the premise that the robot should maximize its fitness, we studied the correlations between sensory data in different modalities and fitness values. We found that this correlation structure can serve as a context-dependent weighting of the importance of individual sensory channels that allows to define such a metric. In a collision-avoidance scenario we demonstrate that this results in (i) faster learning of successful actions, (ii) an acquired differentiation between sensory modalities, (iii) the possibility to use the full sensors resolution without quantization or compression, and (iv) a means to enhance sensor failure resilience.

Keywords: Learning and Adaptive Systems, Sensor Fusion
Abstract: Current robotic systems carry many diverse sensors such as laser scanners, cameras and inertial measurement units just to name a few. Typically such data is fused by engineering a feature that weights the different sensors against each other in perception tasks. However, in a long-term autonomy setting the sensor readings may change drastically over time which makes a manual feature design impractical. A method that can automatically combine features of different data sources would be highly desirable for adaptation to different environments. In this paper, we propose a novel clustering method, coined Layered Affinity Propagation, for automatic clustering of observations that only requires the definition of features on individual data sources. How to combine these features to obtain a good clustering solution is left to the algorithm, removing the need to create and tune a complicated feature encompassing all sources. We evaluate the proposed method on data containing two very common sensor modalities, images and range information. In a first experiment we show the capability of the method to perform scene segmentation on Kinect data. A second experiment shows how this novel method handles the task of clustering segmented colour and depth data obtained from a Velodyne and camera in an urban environment.

Keywords: Space Robotics and Automation, Learning and Adaptive Systems
Abstract: It is well recognized that many scientifically interesting sites on Mars are located in rough terrains. Therefore, to enable safe autonomous operation of a planetary rover during exploration, the ability to accurately estimate terrain traversability is critical. In particular, this estimate needs to account for terrain deformation, which significantly affects the vehicle attitude and configuration. This paper presents an approach to estimate vehicle configuration, as a measure of traversability, in deformable terrain by learning the correlation between exteroceptive and proprioceptive information in experiments. We first perform traversability estimation with rigid terrain assumptions, then correlate the output with experienced vehicle configuration and terrain deformation using a multi-task Gaussian Process (GP) framework. Experimental validation of the proposed approach was performed on a prototype planetary rover and the vehicle attitude and configuration estimate was compared with state-of-the-art techniques. We demonstrate the ability of the approach to accurately estimate traversability with uncertainty in deformable terrain.

Attachments: Video Attachment
Keywords: Space Robotics and Automation, Field Robots, Wheeled Robots
Abstract: Many intriguing science discoveries on planetary surfaces, such as the seasonal flows on crater walls and skylight entrances to lava tubes, are at sites that are currently inaccessible to state-of-the-art rovers. The in situ exploration of such sites is likely to require a tethered platform both for mechanical support and for providing power and communication. Mother/daughter architectures have been investigated where a mother deploys a tethered daughter into extreme terrains. Deploying and retracting a tethered daughter requires undocking and redocking of the daughter to the mother, with the latter being the challenging part. In this paper, we describe a vision-based tether-assisted algorithm for the autonomous re-docking of a daughter to its mother following an extreme terrain excursion. The algorithm uses fiducials mounted on the mother to improve the reliability and accuracy of estimating the pose of the mother relative to the daughter. The tether that is anchored by the mother helps the docking process and increases the system’s tolerance to pose uncertainties by mechanically aligning the mating parts in the final docking phase. A preliminary version of the algorithm was developed and field-tested on the Axel rover in the JPL Mars Yard. The algorithm achieved an 80% success rate in 40 experiments in both firm and loose soils and starting from up to 6 m away at up to 40 radial angle and 20 relative heading. The algorithm does not rely on an initial estimate of the relative pose. The preliminary results are promising and help retire the risk associated with the autonomous docking process enabling consideration in future martian and lunar missions.

Keywords: Space Robotics and Automation, Wheeled Robots, Contact Modelling
Abstract: The wheels of planetary rovers will slip when they climbs up deformable slopes. On the contrary, the wheels will skid in the longitudinal direction in order to generate resistance force to balance the gravity component when a rover moves down the slopes. The wheel-terrain interaction principles of slip versus skid are quite different, but there is little research about the longitudinal skid mechanics and the relationship of it with the slip mechanics. This paper analyzes the problem of longitudinal slip and skid that occur to a wheel on the slopes with the knowledge of terramechanics. The slip and skid mechanics are compared based on experimental results measured by a single wheel testbed. The piece wise linear function is proposed to predict the drawbar pull and resistance moment under both slip and skid conditions. A semi-empirical equation of predicting the skid mechanics according to the slip mechanics is also provided. The models are verified using the experimental data.

Keywords: Field Robots, Robotics in Hazardous Fields
Abstract: During a volcanic activity, it is very dangerous to approach a restricted area. For this reason, robotic remote observation system would be quite useful, and it is particularly urgent for a country with a high degree of volcanic activity, such as Japan. In response to this need, our research group developed a novel multi-D.O.F. tracked vehicle, called ELF, which can conduct observation in a restricted volcanic area. The robot essentially consists of six tracks, and it has eleven actuators that change its configuration. These actuators enable the robot to assume various configurations, which increase its ability to traverse weak and rough terrains in the area around a volcano. In this research, we propose one configuration of the robot, in which the surface of the contact plane at the bottom of the track is horizontal, which is advantageous for traversing a weak slope. The feasibility of this design was verified in a field experiment on Mt. Kushigata, on the island of Izu-Oshima, and in a simulated volcanic field that was filled with pumice stones.

Keywords: Field Robots, Robotics in Agriculture and Forestry, Multi-Robot Coordination
Abstract: Off-road mobile robotics may have important interest in many fields of application such as agriculture or surveillance. In this paper, the control of a fleet of wheeled mobile robots, equipped with RTK-GPS sensors and communicating through WiFi, is investigated. The focus is particularly set on the control of a formation of several robots with respect to a reference trajectory, previously learned or computed off-line. Non-linear exact transformations permit to achieve a laterally and longitudinally decoupled model; from which the control of steering angle and velocity are derived separately in order to ensure the desired formation shape. Since the control of lateral distance to the reference trajectory is based on other works, only the longitudinal control is detailed in this paper. It is based on an adaptive and predictive control algorithm, in order to account for both sliding and actuator delays. The experimental results demonstrate the capabilities of the proposed approach.

Keywords: Motion and Path Planning, Motion Control
Abstract: This paper offers a method to compute the control inputs for an all-wheel drive vehicle that moves along a specified path on rough terrain. The focus of this paper is on longitudinal motion only, using a half-car model with no suspensions. For a given path, we first compute the range of the admissible speeds and accelerations at every point along the path, subject to vehicle dynamics and constraints on the wheel/ground forces. A feasible velocity profile along the path is then computed to respect the admissible speeds and accelerations and satisfy given boundary conditions. While the velocity profile represents the accelerations of the center of mass, it remains to determine the control inputs (torques) for the two independent wheels. The challenge stems from the longitudinal model being an indeterminate system, having two control inputs but only one degree-of-freedom along the specified path. This inherent indeterminisity is resolved by adding a virtual suspension to the rigid vehicle model, which allows to explicitly compute the two individual wheel torques. The method is demonstrated for a vehicle moving at the time optimal speeds over a bump. A dynamic simulation of the vehicle with a stiff suspension shows that the two wheels maintain contact with the ground at all times, despite moving at the ultimate speeds. It is also shown that the all-wheel-drive model produces a larger set of admissible speeds and accelerations, and hence results in faster speeds and shorter motion times than the single drive (front or rear) model.

Keywords: Dynamics, Calibration and Identification
Abstract: This paper presents the dynamic parameter identification of the 7-DOF WAM TM Arm using a novel physically consistent regression technique. Due to model and data errors, physically impossible parameters can arise with classical estimations methods. Such infeasible estimations cannot be used in robot control or simulation. This paper proposes a semidefinite programming (SDP) reformulation of the classical ordinary least squares method. This enables the inclusion of constraints guaranteeing physically feasible solutions only. The SDP method efficiently finds the feasible solution with the lowest regression error. Regression data processing issues related to the WAM robot are also addressed.

Keywords: Dynamics, Hydraulic/Pneumatic Actuators, Animation and Simulation
Abstract: This paper presents a fast computation method of hydraulic robots dynamics and shows the effectiveness in design optimization that needs a lot of repetitive simulations. First, an exact simplification of the conventional representation of hydraulic robots with external forces is presented based on the Casimir function. Second, a further exact simplification is given via an integration by parts of the Hamiltonian function as a novel structural property and a new representation of the hydraulic robots is proposed. Third, the proposed representation and the conventional representation are compared with each other with respect to computational cost and the effectiveness of the proposed representation is confirmed in design optimization.

Attachments: Video Attachment
Keywords: Dynamics, Mechanism Design, Parallel Robots
Abstract: Much attention has not been paid to analysis of open-loop stability for gravity counter-balancing of parallel mechanisms or closed-chain mechanisms. The open-loop stability is crucial especially in passively counter-balanced mechanisms where no actuators are involved. Smart hands-on device is such an example. A general stiffness model is derived for general closed-chain mechanism including counter-weight model. As a measure of the open-loop stability, we employ the determinant of the stiffness matrix. A parallel mechanism having 3 translational DOF (degree of freedom) is employed as an exemplary device. An antagonistically counter-balancing is found the most stable method. We conduct dynamic simulation and experiment to demonstrate the open-loop stability.

Keywords: Dynamics, Biologically-Inspired Robots, Motion Control
Abstract: This paper describes a feedback excitation control system with consideration of gravity, which is a control method to obtain high kinetic energy by utilizing passive potential energy. In the case of a robot that have series elastic joints, peak kinetic energy becomes higher than that of a rigid robot with same motors. We have proposed the feedback excitation control for horizontal multiple-joint robots in previous work. In this paper, we extend the feedback excitation control to systems that are affected by gravity, and we analyze the feedback excitation control system from the viewpoint of linear vibration mode. Validity of the proposed ’coordinate or opposite phase controller’ is suggested by the modal analysis. We examine effective excitation controllers to utilize gravitational and elastic potential energy by simulations and experiments.

Keywords: Dynamics, Force Control, Contact Modelling
Abstract: In the model of the constrained dynamic system of a rigid robot contacting with rigid environment, constrained forces can be expressed as an algebraic function of states (instantaneous process) and a redundancy existing in constraint dynamics (constraint redundancy). Using these results, a force and position control law is proposed by taking the advantages of the redundancy of input generalized forces to the constrained forces and instantaneous process without involving any force sensor, using dual nature of constraint motion stated in this document. Then proof confirming by Lyapunov method that the exerting force equals instantaneously and constantly to desired one and that the motion of robot’s hand in a movable space converges to desired hand’s position. The effectiveness has been confirmed by a 2-link robot in simulation.

Keywords: Robot Safety
Abstract: Risk assessment considering child injury risks in collisions should be performed before introducing mobile robots into human-robot collaborative environments. This paper provides data for estimating the injury level and the injury probability for the risk assessment using information from automotive-accident research. Experiments representing collisions between six-year-old children and mobile robots were conducted using an automotive crash-test dummy. Mechanical data on head, neck, and chest of the dummy were measured. The results indicate that robot manufacturers should consider head injuries in collisions before introducing their mobile robots into environments with children.

Keywords: Robot Audition
Abstract:

Keywords: Localization, Human detection and tracking, Voice, Speech Synthesis and Recognition
Abstract: A theoretically grounded scheme to Direction of Arrival (DOA) estimation and Source Activity Detection (SAD) is proposed, on the basis of a pair of microphones. The method can capture the effects of the robot’s scatterers, if any. The DOA estimator takes place within a probabilistic framework and outputs the Maximum Likelihood Estimate (MLE) of the DOA with respect to the collected audio data. Besides, the SAD relies on statistical identification. The behavior of the estimator is studied under various operating modes, considering free- field propagation and scattering by a rigid spherical head. Experimental results validate the approach.

Attachments: Video Attachment
Keywords: Human detection and tracking, Voice, Speech Synthesis and Recognition, Human-Robot Interaction
Abstract: This paper deals with speaker localization in two dimensions from a mobile binaural head. A bootstrap particle filtering scheme is used to perform active localization, i.e. to infer source location by fusing the binaural perception with the sensor motor commands. It relies on an original pseudo-likelihood of the source azimuth which captures both the interaural level and phase differences. Since the pseudo-likelihood is discrete, it is fitted with a mixture of circular distributions in order to enhance its resolution. For the fitting task two mixtures are compared and evaluated, namely the mixture of von Mises and wrapped Cauchy distributions. Furthermore, a solution is presented for calculating the von Mises curvefitting with low uncertainty, since the direct implementation can quickly surpass double precision floating number representation. The performance of the filter is compared using both the raw and fitted pseudo-likelihoods on experiments recorded in an acoustically prepared room with ground-truth obtained from a motion capture system. The results show that the proposed algorithm successfully localizes the speaker with an advantage in the direction of the fitted von Mises mixture likelihood.

Keywords: Localization, Humanoid Robots, Biomimetics
Abstract: This paper proposes a sound localization algorithm inspired by a cross-channel algorithm first proposed by MacDonald et. al in 2008. The original algorithm assumes that the Head Related Transfer Functions (HRTFs) of the robot head are precisely known, which is rarely the case in practice. Following the idea that any head is more or less spherical, the above assumption is relaxed by using HRTFs computed using a simple spherical head model with the same head radius as the robot head. In order to evaluate the proposed approach in realistic noisy conditions, an isotropic noise field is also computed and a precise definition of the Signal to Noise Ratio (SNR) in a binaural context is outlined. All these theoretical developments are finally assessed with simulated and experimental signals. Despite its simplicity, the proposed approach appears to be robust to noise and to provide reliable sound localization estimations in the azimuthal plane.

Keywords: Localization, Humanoid Robots, Biomimetics
Abstract: Sound source localization is an important feature designed and implemented on robots and intelligent systems. Like other artificial audition tasks, it is constrained to multiple problems, notably sound reflections and noises. This paper presents a sound source azimuth estimation approach in rever- berant environments. It exploits binaural signals in a humanoid robotic context. Interaural Time and Level Differences (ITD and ILD) are extracted on multiple frequency bands and combined with a neural network-based learning scheme. A cue filtering process is used to reduce the reverberations effects. The system has been evaluated with simulation and real data, in multiple aspects covering realistic robot operating conditions, and was proven satisfying and effective as will be shown and discussed in the paper.

Attachments: Video Attachment
Keywords: Unmanned Aerial Vehicles, Control Architectures and Programming, Aerial Robotics
Abstract: In this work, we present a powerful, albeit simple position control approach for Micro Aerial Vehicles (MAVs) targeting specifically multicopter systems. Exploiting the differential flatness of four of the six outputs of multicopters, namely position and yaw, we show that the remaining outputs of pitch and roll need not be controlled states, but rather just need to be known. Instead of the common approach of having multiple cascaded control loops (position - velocity - acceleration/attitude - angular rates), the proposed method employs an outer control loop based on dynamic inversion, which directly commands angular rates and thrust. The inner control loop then reduces to a simple proportional controller on the angular rates. As a result, not only does this combination allow for higher bandwidth compared to common control approaches, but also eliminates many mathematical operations (only one trigonometric function is called), speeding up the necessary processing especially on embedded systems. This approach assumes a reliable state estimation framework, which we are able to provide with through previous work. As a result, with this work, we provide the missing elements necessary for a complete approach on autonomous navigation of MAVs.

Keywords: Aerial Robotics, Motion and Path Planning, Unmanned Aerial Vehicles
Abstract: This paper addresses the problem of motion planning for fast, agile flight through a dense obstacle field. A key contribution is the design of two families of motion primitives for aerial robots flying in dense obstacle fields, along with rules to stitch them together. The primitives are obtained by solving for the flight dynamics of the aerial robot, and explicitly account for limited agility using time delays. The first family of primitives consists of turning maneuvers to link any two points in space. The locations of the terminal points are used to obtain closed-form expressions for the control inputs required to fly between them, while accounting for the finite time required to switch between consecutive sets of control inputs. The second family consists of aggressive turn-around maneuvers wherein the time delay between the angle of attack and roll angle commands is used to optimize the maneuver for the spatial constraints. A 3-D motion planning algorithm based on these primitives is presented for aircraft flying through a dense forest

Keywords: Aerial Robotics, Cooperating Robots, Path Planning for Multiple Mobile Robots or Agents
Abstract: This paper presents a cooperative system architecture that extends the flight duration of multiple gliding fixed-wing Unmanned Aerial Vehicles (UAVs) for long endurance missions. The missions are defined by a set of Points of Interest (PoI) and UAVs should pass through them. A module to detect and identify thermals is implemented to exploit their energy and extend the flight duration, known as static soaring. A collision-free trajectory planner based on the RRT* (Optimal Rapidlyexploring Random Trees) planning algorithm is implemented. The proposed system allows applications in real time because of its low computational needs. Simulations and experiments carried out in the airfield of La Cartuja (Seville, Spain) show the performance and advantages of the proposed system.

Keywords: Unmanned Aerial Vehicles, Aerial Robotics, Unmanned Aerial Systems
Abstract: In this work, we consider the optimal path of a fixed-wing unmanned aerial vehicle (UAV) tracking a mobile surface target. One of the limitations of fixed-wing UAVs in tracking mobile targets is the lack of hovering capability when the target moves much slower than the minimum UAV speed, requiring the UAV maintain an orbit about the target. In this paper, we propose a method to find the optimal policy for fixed-wing UAVs to minimize the location uncertainty of a mobile target. Using a grid-based Markov Decision Process (MDP), we use an off-line policy iteration algorithm to find an optimal UAV path in a coarse discretized state space, followed by an on-line policy iteration algorithm that applies a finer grid MDP to the region of interest to find the final optimal UAV trajectory. We validate the proposed algorithm using computer simulations. Comparing the simulation results with other methods, we show that the proposed method has up to 13% decrease in error uncertainty than ones resulted using conventional methods.

Keywords: Unmanned Aerial Vehicles, Visual Tracking, Computer Vision
Abstract: In this study, we focus on the problem of landing an unmanned aerial vehicle (UAV) in unknown and Global Navigation Satellite System(GNSS)-denied environments based on an infrared stereo vision system. This system is fixed on the ground and used to track the UAV's position during the landing process. In order to enlarge the search field of view (FOV), a pan-tilt unit (PTU) is employed to actuate the vision system. The infrared camera is chosen as the exteroceptive sensor for two main reasons: first, it can be used under all weather conditions and around the clock; second, infrared targets can be tracked based on infrared spectrum features at a lower computational cost compared to tracking texture features in visible spectrum. State-of-the-art active contour based algorithms and the mean shift algorithm have been evaluated with regard to detecting and tracking an infrared target. Field experiments have been carried out using an unmanned quadrotor and a fixed-wing unmanned aircraft, with both qualitative and quantitative evaluations. The results demonstrate that our system can track UAVs without artificial markers and is sufficient to enhance or replace the GNSS-based localization in GNSS-denied environment or where its information is inaccurate.

Attachments: Video Attachment
Keywords: Unmanned Aerial Systems, Aerial Robotics, Unmanned Aerial Vehicles
Abstract: In this paper, we present a multi-sensor system for automatic landing of fixed wing UAVs. The system is composed of a high precision aircraft controller and a vision module which is currently used for detection and tracking of runways. Designing the system we paid special attention to its robustness. So, the runway detection algorithm uses a maximum amount of information in images and works with high level geometrical models. It allows to detect a runway under different weather conditions even if only a small part is visible in the image. In order to increase landing reliability under not optimal wind conditions, an additional loop was introduced into the altitude controller. All control and image processing is performed onboard. The system has been successfully tested in flight experiments with two different fixed wing platforms at various weather conditions, in summer, fall and winter.

Attachments: Video Attachment
Keywords: Grasping, Localization, Force and Tactile Sensing
Abstract: Robotic hands are a key component of humanoids. Initially more fragile and larger than their human counterparts, the technology has evolved and the latest generation is close to the human hand in size and robustness. However, it is still disappointing to see how little robotic hands are able to do once the grasp is acquired due to the difficulty to obtain a reliable pose of the object within the palm. This paper presents a novel method based on a particle filter used to estimate online the object pose. It is shown that the method is robust, accurate and handles many realistic scenario without hand crafted rules. It combines an efficient collision checker with a few very simple ideas, that require only a basic knowledge of the geometry of the objects. It is shown, by experiments and simulations, that the algorithm is able to deal with inaccurate finger position measurements and can integrate tactile measurements. The method greatly enhances the performance of common manipulation operations, such as a pick and place tasks, and boosts the sensing capabilities of the robot.

Attachments: Video Attachment
Keywords: Grasping, Multifingered Hands
Abstract: This work deals with grasping using an anthropomorphic hand. The main idea is to easily compute a grasp for a robotic hand in the context of a given task. This paper describes a method that does not require learning. Starting from works in the neuroscience field on human hand postural synergies, we introduce a two-level algorithm that uses a mathematical model of relationships between muscles and degrees-of-freedom of the hand and a set of five parameters to define synergies between muscles according to some grasp properties taken from an existing taxonomy of grasps. The two-level architecture presented in this paper aims to provides the flexibility needed for working with a real robotic hand in a large research project. This algorithm is validated both in simulation using Gazebo and on the Shadow Robot Hand.

Attachments: Video Attachment
Keywords: Grasping, Manipulation Planning and Control, Integrated Planning and Control
Abstract: Caging can offer robustness to uncertainties in grasping. If a robotic hand is designed based on the idea of caging, it would probably work well with noisy perception devices and low-quality control. This paper takes into account these merits and designs and implements a gripping hand based on the idea of caging. The gripping hand is concise and offers a low-cost alternative to co-operate with noisy data and low-quality control. According to previous work, we need four fingers to cage any 2D objects. That is to say, if each finger has one, two or three degree of freedoms, we will totally need four, eight or twelve actuators. The large number of actuators would be costly. This paper simplify the number of actuators into one by quantitatively analyzing finger formations with caging tests conducted on both random objects and objects from MPEG-7 shape database. It successfully lowers costs while maintains high performance. Following the simplified one-actuator design we implement a gripping hand by modifying a SCHUNK RH707 hand and carried out experiments with a manipulator built on the Neuronics Katana arm. The one-actuator gripping hand could work well with common depth cameras (Swiss Ranger) and pick up various objects. It bridges the gap between caging theories and applications and demonstrates the merits of caging.

Attachments: Video Attachment
Keywords: Grasping, Dexterous Manipulation, Gripper and Hand Design
Abstract: This paper proposes a novel approach for the synthesis of grasps of objects whose geometry can be observed only in the presence of noise. We focus in particular on the problem of generating caging grasps with a realistic robot hand simulation and show that our method can generate such grasps even on complex objects. We introduce the idea of using geodesic balls on the object’s surface in order to approximate the maximal contact surface between a robotic hand and an object. We define two types of heuristics which extract information from approximate geodesic balls in order to identify areas on an object that can likely be used to generate a caging grasp. Our heuristics are based on two scoring functions. The first uses winding angles measuring how much a geodesic ball on the surface winds around a dominant axis, while the second explores using the total discrete Gaussian curvature of a geodesic ball to rank potential caging postures. We evaluate our approach with respect to variations in hand kinematics, for a selection of complex real-world objects and with respect to its robustness to noise.

Keywords: Grasping, Path Planning for Manipulators, Integrated Planning and Control
Abstract: In this work, we address the problem of simultaneous clasp and motion planning on unknown objects with holes. Clasping an object enables a rich set of activities such as dragging, toting, pulling and hauling which can be applied to both soft and rigid objects. To this end, we define a virtual linking measure which characterizes the spacial relation between the robot hand and object. The measure utilizes a set of closed curves arising from an approximately shortest basis of the object’s first homology group. We define task spaces to perform collision-free motion planing with respect to multiple prioritized objectives using a sampling-based planing method. The approach is tested in simulation using different robot hands and various real-world objects.

Keywords: Grasping, Multifingered Hands, Variable Stiffness Actuator Design and Control
Abstract: In this paper, we propose a general method to achieve a desired grasp compliance acting both on the joint stiffness values and on the hand configuration, also in the presence of restrictions caused by synergistic underactuation. The approach is based on the iterative exploration of the equilibrium manifold of the system and the quasi-static analysis of the governing equations. As a result, the method can cope with large commanded variations of the grasp stiffness with respect to an initial configuration. Two numerical examples are illustrated. In the first one, a simple 2D hand is analyzed so that the obtained results can be easily verified and discussed. In the second one, to show the method at work in a more realistic scenario, we model grasp compliance regulation for a DLR/HIT hand II grasping a ball.

Keywords: Motion and Trajectory Generation, Integrated Planning and Control, Robot Safety
Abstract: This paper presents a method to develop trajectories which remain optimally insensitive to sudden changes in dynamics. The approach is applied to two example systems that model a vehicle's attempt to navigate through potentially hazardous areas of the state space. Through these simplified examples, we show how to automatically plan trajectories which either avoid or adjust controls to safely pass through critical regions of the state space.

Keywords: Flexible Arms, Biologically-Inspired Robots, Motion and Path Planning
Abstract: In this paper we propose a methodology to control a novel class of actuators that we called passive noise rejection variable stiffness actuators (pnrVSA). Differently from nowadays classical VSA designs, this novel class of actuators mimics the human musculoskeletal ability to increase noise rejection without relying on feedback. To fully highlight the potentialities behind these actuators we consider movement planning under two constraints: (1) absence of feedback, i.e. purely open-loop planning; (2) uncertain dynamic model. Under these constraints, movement planning can be formalized as an open-loop stochastic optimal control. Due to the lack of classical methods forcing the open-loop nature of the computed solution, we used here a slight modification of available methodologies based on importance sampling of trajectories using forward diffusion processes. Simulations show that the proposed algorithm can be effectively used to plan open-loop movements with pnrVSA. In particular, two different scenarios are considered: the control of a single joint pnrVSA and the control of a two degrees of freedom planar arm equipped with antagonist pnrVSAs at each joint. In both cases, movement has to be planned in presence of uncertain dynamics for unstable tasks. It is shown that open-loop stochastic optimal control can modulate the intrinsic stiffness of the system to cope with both instability and noise.

Keywords: Flexible Arms, Joint/Mechanism, Biologically-Inspired Robots
Abstract: Designing intrinsically elastic robots have recently attracted a lot of attention. Inspired by the elasticity in muscles, these designs aim at enabling robots to imitate human or animal motions during various tasks such as hopping, running, etc. In particular, reaching peak velocities using the stored energy in the springs is of great interest. Applying optimal control theory, we investigate the problem of maximizing the link velocity and discuss in particular how the optimal control strategy for visco-elastic joints is affected by mechanical damping.

Keywords: Redundant Robots, Dynamics, Compliance and Impedance Control
Abstract: Robots with a large number of actuated degrees of freedom are usually redundant w.r.t. a given task. That kinematic redundancy can be utilized to execute additional tasks simultaneously, e.g. via null space projection techniques. We introduce a new representation of hierarchical robot dynamics which are based on a set of particular null space velocities. Dynamic consistency is preserved, and strict compliance with the order of priority is ensured at all times due to a power-conserving cancellation of coupling terms by active control. No external force measurements have to be performed. We show asymptotic stability of the generic closed-loop system with an arbitrary number of hierarchy levels. Several simulations confirm our results.

Keywords: Underactuated Robots, Unmanned Aerial Systems, Unmanned Aerial Vehicles
Abstract: In this paper, a quaternion based nonlinear output feedback tracking controller is developed to address the attitude and altitude tracking problem of a quadrotor unmanned aerial vehicle (UAV) which is subject to structural uncertainties and unknown external disturbances. A set of filters are introduced to provide estimation for the unmeasurable quadrotor UAV's angular and translational velocity signals. The Lyapunov based stability analysis ensures that a semi-global asymptotic tracking result is achieved and all closed loop states remain bounded with a suitable choice of control gains.

Keywords: Behaviour-Based Systems, Planning, Scheduling and Coordination, Service Robots
Abstract: Behavior-based robotic manipulators are very flexible since they can perform many different tasks without reprogramming. Unfortunately none of the existing approaches is able to interweave multiple manipulation tasks and execute them reliably at the same time, enabeling e.g. an intuitive human-robot cooperation. To bridge this gap, we suggest a novel reactive behavior-based architecture. For this, we transfer the multitasking concept from modern computer operating systems to the robot and use a resource based approach to coordination and synchronization. With this, we are able to safely run multiple competing behaviors on a robot. Due to the design of the behaviors, new behaviors can easily be added to the system. The behaviors can be interrupted by other behaviors in order to react properly to a dynamic environment. Later, the interrupted behaviors are resumed in such a way that the system keeps a consistent state.

Attachments: Video Attachment
Keywords: Surgical Robotics, Force Control, Mechanism Design
Abstract: This paper describes the design and implementation of a robotic vision system for single-site surgery. The system is composed of a wireless miniature camera robot with magnetic pan and tilt capabilities, and an external robotic arm to guide the camera along the abdominal wall. The camera robot is provided with a set of magnets, and a magnetic holder is attached at the end effector of the manipulator. This way, the camera robot can be displaced to obtain additional viewpoints of the abdominal cavity by displacing the external manipulator. The first prototype of the camera robot with an embedded LED lighting system is described. To properly displace the robotic arm over the abdominal wall, a hybrid force-position control has been developed, which includes a torque compensation module in order to obtain an appropriate orientation of the end effector. The contact surface has been assumed to be an elastic model, which stiffness matrix is estimated with a recurrent least squares algorithm. Finally, an in-vitro experiment to validate the control scheme proposed is presented.

Keywords: Medical Robots and Systems, Cooperative Manipulators, Surgical Robotics
Abstract: Image-guided radiation therapy (IGRT) involves two main procedures, performed in different rooms on different days: (1) treatment planning in the simulator room on the first day, and (2) radiotherapy in the linear accelerator room over multiple subsequent days. Both the simulator and the linear accelerator include CT imaging capabilities, which enables both treatment planning and reproducible patient setup, but does not provide good soft tissue contrast or allow monitoring of the target during treatment. We propose a cooperatively-controlled robot to reproducibly position an ultrasound (US) probe on the patient during simulation and treatment, thereby improving soft tissue visualization and allowing real-time monitoring of the target. A key goal of the robotic system is to produce consistent tissue deformations for both CT and US imaging, which simplifies registration of these two modalities. This paper presents the robotic system design and describes a novel control algorithm that employs virtual springs to implement guidance virtual fixtures during "hands on" cooperative control.

Keywords: Medical Robots and Systems, Surgical Robotics, Path Planning for Manipulators
Abstract: Concentric tube robots are continuum robots that can navigate natural pathways to reach locations deep inside the human body. Their operation is based on rotating and telescopically actuating concentric tubes to achieve robot tip pose control. During tube manipulation, the elastic energy stored in the robot structure may give rise to unstable robot configurations and loss of control. This can occur, in particular, for highly curved and elongated tubes that are required for certain surgical interventions. This paper presents a path planning methodology that allows the utilization of such generally unstable concentric tube robots by ensuring that they operate in their stable configuration regions.

Attachments: Video Attachment
Keywords: Medical Robots and Systems, Mechanism Design
Abstract: In this paper, tension propagation analysis of a newly designed multi-DOF robotic platform for single-port access surgery (SPS) is presented. The analysis is based on instantaneous kinematics of the proposed 6-DOF surgical instrument, and provides the decision criteria for estimating the payload of a surgical instrument according to its pose changes and specifications of a driving-wire. Also, the wire-tension and the number of reduction ratio to manage such a payload can be estimated, quantitatively. The analysis begins with derivation of the power transmission efficiency through wire-interfaces from each instrument joint to an actuator. Based on the energy conservation law and the capstan equation, we modeled the degradation of power transmission efficiency due to 1) the reducer called wire-reduction mechanism, 2) bending of proximal instrument joints, and 3) bending of hyper-redundant guide tube. Based on the analysis, the tension of driving-wires was computed according to various manipulation poses and loading conditions. In our experiment, a newly designed surgical instrument successfully managed the external load of 1kgf, which was applied to the end effector of a surgical manipulator.

Attachments: Video Attachment
Keywords: Medical Robots and Systems, Force and Tactile Sensing, Localization
Abstract: Magnetically driven wireless capsule endoscopy (WCE) represents one of the last achievements in the research of minimally invasive tools for gastrointestinal tract (GI) diagnosis. Recently, capsule localization methodologies have been employed to enable system autonomy maintaining a magnetic link with the device and managing interaction forces with GI tissues. To achieve these objectives, the locomotion platforms exploit automatic motion in some degrees of freedom and unsupervised contact with the external patient abdomen can occur. In this paper safety issues are faced; in particular a safety system, able to monitor pressure with patient abdomen, has been designed, characterized, and integrated with a magnetically driven WCE locomotion platform. New technologies, such as smart textiles, have been employed as sensible element. The proposed system showed promising results in controlling the pressure exerted on the abdomen respecting safety limits and increasing the efficiency and range of locomotion.

Keywords: Computer-assisted diagnosis and therapy, Medical Systems, Healthcare, and Assisted Living, Computer Vision
Abstract: Wireless capsule endoscopy (WCE) is a recently developed revolutionary medical technology which records the video of human’s digestive tract noninvasively. However, reviewing a WCE video is a tired and time-consuming task for clinicians. Thus, WCE video automatic segmentation methods are emerging to reduce the review time for clinicians. In our previous work, a two-level WCE video segmentation approach has been proposed, which provides a novel approach to localize the boundaries more exactly and efficiently. However, it has an unsatisfactory performance in the small intestine/large intestine boundary detection. In this paper, we propose new features and an improved classifier to improve the previous two-level segmentation algorithm. In the rough level, color feature is utilized to draw a dissimilarity curve and an approximate boundary has been obtained. At the same time, training data for fine level can be directly labeled and collected between the two approximate boundaries of organs to overcome the difficulty of training data acquisition. In the fine level, a novel color uniform local binary pattern (CULBP) algorithm is proposed, which includes two kinds of patterns, color norm patterns and color angle patterns. The CULBP feature is more robust to variation of illumination and more discriminative for classification. Moreover, in order to elevate the performance of SVM classifier we proposed the Ada-SVM classifier which using RBFSVMs as component of Adaboost classifier. At last, an analysis of classification results of the Ada-SVM classifier is carried out to segment the WCE video into several meaningful parts, stomach, small intestine and large intestine. The experiments demonstrate a promising performance of the proposed method. The average precision and recall are as high as 91.37% and 88.50% in stomach/small intestine classification, 90.35% and 97.28% in small intestine/ large intestine classification.

Attachments: Video Attachment
Keywords: Motion and Trajectory Generation
Abstract: This paper proposes an off-line periodic motion pattern design method using dimensional reduction. A human periodic motion is measured by a motion capture system, and it is projected onto a low dimensional space based on principal component analysis. The low dimensional motion pattern is modified, so that the high dimensional motion pattern satisfies the motion conditions, dynamical consistency and joint angle and torque limitations. The proposed method is applied to the motion pattern design of the planar bipedal robot. The moon-walk performed by a human is transformed to the robot motion. In this case, the motion conditions are the kinematic closed loop condition and the ground contact states of foot links. The floor reaction force condition and the satisfaction of the motion equation are given for dynamical consistency.

Keywords: Motion and Trajectory Generation
Abstract: Recently, the double generating function method for finite time linear quadratic optimal control problems was proposed. This paper applies it to the on-demand optimal gaits generation of a compass biped robot walking on the level ground. The double generating function method is employed to generate reference optimal gaits and inputs considering the energy consumption by linearizing the compass biped robot. The simulation result shows that the modeling error caused by the linearization is small when the robot walks with a reasonable step length and a appropriate time period. This implies that the optimal states and inputs for the linearized system can be treated as the optimal ones for the original nonlinear system. The biggest advantage of the double generating function method is that it can generate a parametrization of optimal gaits for different boundary conditions and different time periods. Therefore, it is very useful to generate the optimal states and inputs on demand and in real time for the real biped robots.

Keywords: Legged Robots, Dynamics, Motion Control
Abstract: In this paper, we derive the analytical solution to the transition function of the state error in 1-DOF semi-passive dynamic walking for understanding how the gait stability changes according to acceleration or deceleration. We introduce the model of an active rimless wheel (RW) as the simplest walker for analysis and linearize the equation of motion incorporating a simple control torque. Through mathematical investigations, we finally derive the analytical solution to the transition function of the state error for the stance phase as a function only of the control parameters. We discuss the accuracy of the solution obtained through comparison with the values numerically-integrated in the linearized and the nonlinear walking models.

Attachments: Video Attachment
Keywords: Legged Robots, Dynamics, Motion Control
Abstract: It was clarified that limit cycle walkers can improve the gait efficiency by using the oscillatory effect of a wobbling mass moving in the body frame. In this research, we investigate the effects of a 2-DOF wobbling mass on the gait properties. As the simplest walker for analysis, we introduce the model of a planar eight-legged rimless wheel (RW) with a passive 2-DOF wobbling mass that is connected to the RW incorporating a spring and a damper. Through numerical simulations, we analyze changes in the gait properties with respect to the system parameters such as the slope angle and the elastic coefficient.

Attachments: Video Attachment
Keywords: Compliance and Impedance Control, Adaptive Control, Humanoid and Bipedal Locomotion
Abstract: This paper investigates how a walker could estimate the variability of an arbitrary set of state variables when migrating on visco-elastic grounds. The state variables are a function of both the visco-elastic settings of the walking body and soft terrain parameters. A rimless wheel model was developed using a Lagrangian approach in order to obtain analytical solutions for migration across ground conditions. An algorithm was then developed to determine the steady value of the variables as a function of the difference in ground and hub parameters involved in the migration. A generalised migration metaparameter, DELTA
g, function of this difference, was then extrapolated using polynomial approximation.
DELTAg can be used to estimate the expected variability at a state given information on actual and previous ground parameters. A second parameter, DELTA
h, describing local variability of a given state on a given terrain, is used to generate a predictive algorithm capable of stabilising the rimless wheel setup when subject to an abrupt change in ground parameters. We actuate the rimless wheel with a constant torque leaving it to develop any speed profile for a given visco-elastic impedance distribution of the ground and its own vertical visco-elastic impedance. The ground is altered depending on the two migration meta-parameters (
g and
r), ensuring both local and migration stability.

Attachments: Video Attachment
Keywords: Legged Robots, Dynamics, Motion Control
Abstract: This paper investigates modeling and control of a limit cycle walker that walks sliding on the ice. We introduce the model of an underactuated spoked walker for analysis and analyze the collision model on the assumption of sliding contact with the ground to identify the condition for achieving instantaneous exchange of the stance leg. We also develop the equation of motion incorporating dynamic friction in sliding contact. Numerical simulations show that the walker can generate stable walking gaits by applying a simple control of the torso.

Keywords: Human-Robot Interaction, Robot Companions and Social Human-Robot Interaction, Learning from Demonstration
Abstract: Mobile service robots are envisioned to operate in environments that are populated by humans and therefore ought to navigate in a socially compliant way. Since the desired behavior of the robots highly depends on the application, we need flexible means for teaching a robot a certain navigation policy. We present an approach that allows a mobile robot to learn how to navigate in the presence of humans while it is being tele-operated in its designated environment. Our method applies feature-based maximum entropy learning to derive a navigation policy from the interactions with the humans. The resulting policy maintains a probability distribution over the trajectories of all the agents that allows the robot to cooperatively avoid collisions with humans. In particular, our method reasons about multiple homotopy classes of the agents' trajectories, i.e., on which sides the agents pass each other. We implemented our approach on a real mobile robot and demonstrate that it is able to successfully navigate in an office environment in the presence of humans relying only on on-board sensors.

Keywords: Navigation, Motion and Trajectory Generation, Industrial Robots
Abstract: Automation of logistics tasks for small lot sizes and flexible production processes requires intuitive and easy-to-use systems that allow non-expert shop floor workers to naturally instruct transportation systems. To this end, we present a novel laser-based scheme for teach-and-repeat of mobile robot trajectories that relies on scan matching to localize the robot relative to a taught trajectory, which is represented by a sequence of raw odometry and 2D laser data. This approach has two advantages. First, it does not require to build a globally consistent metrical map of the environment, which reduces setup time. Second, the direct use of raw sensor data avoids additional errors that might be introduced by the fact that grid maps only provide an approximation of the environment. Real-world experiments carried out with a holonomic and a differential drive platform demonstrate that our approach repeats trajectories with an accuracy of a few millimeters. A comparison with a standard Monte Carlo~localization approach on grid maps furthermore reveals that our method yields lower tracking errors for teach-and-repeat tasks.

Keywords: Navigation, Autonomous Agents, Reactive and Sensor-Based Planning
Abstract: A robot with limited sensor range has two competing mission objectives: (1) Reach a global goal, (2) Opportunistically forage while en route to that goal. For example, an unmanned aircraft must visit a valuable target and then return to friendly territory, while also attempting to eliminate hostile targets that are detected by on-board sensors along the way. Each foraging act causes a deviation from the shortest path to the long-term goal, with consequences for path length, mission duration, and fuel usage. We analytically calculate and/or bound the expected distance the robot actually travels. In particular, while using either of two non-trivial greedy strategies: (A) forage the point that minimizes goal-heading deviation. (B) forage the closest point ahead of the robot. Our results generalize to problems in higher dimensional spaces.

Keywords: Visual Navigation, SLAM, Aerial Robotics
Abstract: This paper describes an integrated navigation sensor module, including a camera, a laser scanner, and an inertial sensor, for unmanned aerial vehicles (UAVs) to fly both indoors and outdoors. The camera and the gimbaled laser sensor work in a complementary manner to extract feature points from the environment around the vehicle. The features are processed using an online extended Kalman filter (EKF) in simultaneous localization and mapping (SLAM) algorithm to estimate the navigational states of the vehicle. In this paper, a new method is proposed for calibrating a camera and a gimbaled laser sensor. This calibration method uses a simple visual marker to calibrate the camera and the laser scanner with each other. We also propose a real-time navigation algorithm based on the EKF SLAM algorithm, which is suitable for our camera-laser sensor package. The algorithm merges image features with laser range data for state estimation. Finally, these sensors and algorithms are implemented on our octo-rotor UAV platform and the result shows that our onboard navigation module can provide a real-time three-dimensional navigation solution without any assumptions or prior information on the surroundings.

Keywords: Navigation, Sensor Fusion, Localization
Abstract: In this paper, we present a linear-complexity 3D inertial navigation algorithm using both point and plane features observed from an RGBD camera. In particular, we study the system's observability properties, and prove that: (i) When observing a single plane feature of known direction, the IMU gyroscope bias is observable. (ii) By observing a single point feature, as well as a single plane of known direction but not perpendicular to gravity, all degrees of freedom of the IMU-RGBD navigation system become observable, up to global translations. Next, based on the results of the observability analysis, we design a consistency-improved, observability-constrained (OC) extended Kalman filter (EKF)-based estimator for the IMU-RGBD camera navigation system. Finally, we experimentally validate the superiority of our proposed algorithm compared to alternative methods in urban scenes.

Attachments: Video Attachment
Keywords: Navigation, Localization, Unmanned Aerial Vehicles
Abstract: In this paper, we study the problem of hovering (i.e., absence of translational motion) detection and compensation in Vision-aided Inertial Navigation Systems (VINS). We examine the system’s unobservable directions for two common hovering conditions (with and without rotational motion) and propose a robust motion-classification algorithm, based on both visual and inertial measurements. By leveraging our observability analysis and the proposed motion classifier, we modify existing state-of-the-art filtering algorithms, so as to ensure that the number of the system’s unobservable directions is minimized. Finally, we validate experimentally the proposed modified sliding window filter, by demonstrating its robustness on a quadrotor with rapid transitions between hovering and forward motions, within an indoor environment.

Keywords: Perception for Grasping and Manipulation, Force and Tactile Sensing, Learning and Adaptive Systems
Abstract: Object shape information is an important parameter in robot grasping tasks. However, it may be difficult to obtain accurate models of novel objects due to incomplete and noisy sensory measurements. In addition, object shape may change due to frequent interaction with the object (cereal boxes, etc). In this paper, we present a probabilistic approach for learning object models based on visual and tactile perception through physical interaction with an object. Our robot explores unknown objects by touching them strategically at parts that are uncertain in terms of shape. The robot starts by using only visual features to form an initial hypothesis about the object shape, then gradually adds tactile measurements to refine the object model. Our experiments involve ten objects of varying shapes and sizes in a real setup. The results show that our method is capable of choosing a small number of touches to construct object models similar to real object shapes and to determine similarities among acquired models.

Keywords: Range Sensing, Localization, Perception for Grasping and Manipulation
Abstract: This work is focused on global registration of surface models such as homogeneous triangle meshes and point clouds. The investigated approach utilizes feature descriptors in order to assign correspondences between the data sets and to reduce complexity by considering only characteristic feature points. It is based on the decomposability of rigid motions into a rotation and a translation. The space of rotations is searched with a particle filter and scoring is performed by looking for clusters in the resulting sets of translations. We use features computed from homogeneous triangle meshes and point clouds that require low computation time. A major advantage of the approach proves to be the possible consideration of prior knowledge about the relative orientation. This is especially important when high noise levels produce deteriorated features that are hard to match correctly. Comparisons to existing algorithms show the method's competitiveness, and results in robotic applications with different sensor types are presented.

Attachments: Video Attachment
Keywords: Perception for Grasping and Manipulation, Visual Tracking
Abstract: We address the problem of tracking the 6-DoF pose of an object while it is being manipulated by a human or a robot. We use a dynamic Bayesian network to perform inference and compute a posterior distribution over the current object pose. Depending on whether a robot or a human manipulates the object, we employ a process model with or without knowledge of control inputs. Observations are obtained from a range camera. As opposed to previous object tracking methods, we explicitly model self-occlusions and occlusions from the environment, e.g, the human or robotic hand. This leads to a strongly non-linear observation model and additional dependencies in the Bayesian network. We employ a Rao-Blackwellised particle filter to compute an estimate of the object pose at every time step. In a set of experiments, we demonstrate the ability of our method to accurately and robustly track the object pose in real-time while it is being manipulated by a human or a robot.

Keywords: Performance Evaluation and Benchmarking, Recognition, Computer Vision
Abstract: In this work we propose a method to effectively remove noise from depth images obtained with a commodity structured light sensor. The proposed approach fuses data into a consistent frame of reference over time, thus utilizing prior depth measurements and viewpoint information in the noise removal process. The effectiveness of the approach is compared to two state of the art, single-frame denoising methods in the context of feature descriptor matching and keypoint detection stability. To make more general statements about the effect of noise removal in these applications, we extend a method for evaluating local image gradient feature descriptors to the domain of 3D shape descriptors. We perform a comparative study of three classes of such descriptors: Normal Aligned Radial Features, Fast Point Feature Histograms and Depth Kernel Descriptors; and evaluate their performance on a real-world industrial application data set. We demonstrate that noise removal enabled by the dense map representation results in major improvements in matching across all classes of descriptors as well as having a substantial positive impact on keypoint detection reliability.

Keywords: Robotics in Construction, Field Robots, Grasping
Abstract: This paper proposes a practical framework to estimate whether or not a grapple installed in demolition machines is in a grasp state. Object grasp is a highly difficult task that requires safe and precise operations, so identifying a grasp or non-grasp state is important for assisting an operator. These types of outdoor machines lack visual and tactile sensors, so the proposed framework adopts practically available lever operation and cylinder pressure sensors. The grasp is formed by a grasp motion, which is operations to make the grapple pinch an object, and the grasp state, where the grapple holds the object in any manipulator movements. Thus, the framework determinately confirms the grasp motion through the requisite conditions defined by using sequential changes of binarized operation and pressure data for the grapple and the manipulator, and stochastically confirms the grasp state through the enhancement conditions defined by using force and movement vectors including vertical downward force, movement in the longer direction, and horizontal reciprocating movement. The results of experiments conducted to transport objects using an instrumented hydraulic arm indicated that the proposed framework is effective for identifying grasp/non-grasp with high accuracy, independently of various operators and environments.

Keywords: Grasping, Brain Machine Interface, Human-Robot Interaction
Abstract: There has been considerable interest in producing grasping platforms using non-invasive, low bandwidth brain computer interfaces(BCIs). Most of this work focuses on low level control of simple hands. Using complex hands improves the versatility of a grasping platform at the cost of increasing its complexity. In order to control more complex hands with these low bandwidth signals, we need to use higher level abstractions. Here, we present a user interface which allows the user to combine the speed and convenience of offline pre-planned grasps with the versatility of an online planner. This system incorporates a database of pre-planned grasps with the ability to refine these grasps using an online planner designed for arbitrarily complex hands. Only four commands are necessary to control the entire grasping pipeline, allowing us to use a low cost, noninvasive commercial BCI device to produce robust grasps that reflect user intent. We demonstrate the efficacy of this system with results from five subjects and present results using this system to grasp unknown objects.

Keywords: Learning from Demonstration, Motion and Trajectory Generation, Humanoid Robots
Abstract: In this work, we present the online Quantum Mixture Model (oQMM), which combines the merits of quantum mechanics and stochastic optimization. More specifically it allows for quantum effects on the mixture states, which in turn become a superposition of conventional mixture states. We propose an efficient stochastic online learning algorithm based on the online Expectation Maximization (EM), as well as a generation and decay scheme for model components. Our method is suitable for complex robotic applications, where data is abundant or where we wish to iteratively refine our model and conduct predictions during the course of learning. With a synthetic example, we show that the algorithm can achieve higher numerical stability. We also empirically demonstrate the efficacy of our method in well-known regression benchmark datasets. Under a trajectory Learning by Demonstration setting we employ a multi-shot learning application in joint angle space, where we observe higher quality of learning and reproduction. We compare against popular and well-established methods, widely adopted across the robotics community.

Keywords: Learning from Demonstration, Rehabilitation Robotics, Learning and Adaptive Systems
Abstract: Crafting a proper assistance policy is a difficult endeavour but essential for the development of robotic assistants. Indeed, assistance is a complex issue that depends not only on the task-at-hand, but also on the state of the user, environment and competing objectives. As a way forward, this paper proposes learning the task of assistance through observation; an approach we term Learning Assistance by Demonstration (LAD). Our methodology is a subclass of Learning-by-Demonstration (LbD), yet directly addresses difficult issues associated with proper assistance such as when and how to appropriately assist. To learn assistive policies, we develop a novel probabilistic model that explicitly captures these elements and provide efficient, on-line, training methods. Experimental results on smart mobility assistance - using both simulation and a real-world smart wheelchair platform - demonstrate the effectiveness of our approach; the LAD model quickly learns when to assist (achieving an AUC score of 0.95 after only one demonstration) and improves with additional examples. Results show that this translates into better task-performance; our LAD-enabled smart wheelchair improved participant driving performance (measured in lap seconds) by 20.6s (a speedup of 137%), after a single teacher demonstration.

Keywords: Learning from Demonstration, Human-Robot Interaction, Learning and Adaptive Systems
Abstract: Deploying robots to our day-to-day life requires them to have the ability to learn from their environment in order to acquire new task knowledge and to flexibly adapt existing skills to various situations. For typical real-world tasks, it is not sufficient to endow robots with a set of primitive actions. Rather, they need to learn how to sequence these in order to achieve a desired effect on their environment. In this paper, we propose an intuitive learning method for a robot to acquire sequences of motions by combining learning from human demonstrations and reinforcement learning. In every situation, our approach treats both ways of learning as alternative control flows to optimally exploit their strengths without inheriting their shortcomings. Using a Gaussian Process approximation of the state-action sequence value function, our approach generalizes values observed from demonstrated and autonomously generated action sequences to unknown inputs. This approximation is based on a kernel we designed to account for different representations of tasks and action sequences as well as inputs of variable length. From the expected deviation of value estimates, we devise a greedy exploration policy following a Bayesian optimization criterion that quickly converges learning to promising action sequences while protecting the robot from sequences with unpredictable outcome. We demonstrate the ability of our approach to efficiently learn appropriate action sequences in various situations on a manipulation task involving stacked boxes.

Keywords: Learning from Demonstration
Abstract: We consider the problem of incrementally learning different strategies of performing a complex sequential task from multiple demonstrations of an expert or a set of experts. While the task is the same, each expert differs in his/her way of performing it. We assume that this variety across experts' demonstration is due to the fact that each expert/strategy is driven by a different reward function, where reward function is expressed as a linear combination of a set of known features. Consequently, we can learn all the expert strategies by forming a convex set of optimal deterministic policies, from which one can match any unseen expert strategy drawn from this set. Instead of learning from scratch every optimal policy in this set, the learner transfers knowledge from the set of learned policies to bootstrap its search for new optimal policy. We demonstrate our approach on a simulated mini-golf task where the 7 degrees of freedom Barrett WAM robot arm learns to sequentially putt on different holes in accordance with the playing strategies of the expert.

Attachments: Video Attachment
Keywords: Learning from Demonstration, Human Centered Planning and Control, Medical Robots and Systems
Abstract: We propose a learning-based controller to enable autonomous execution of the eFAST scanning by a lightweight robotic manipulator according to expert demonstrations. The benefits of this approach are two-fold. Firstly, the automatically acquired USS images can be sent to the expert radiologist from a remote location without the need for complex robotic tele-operation. Secondly, the application of learning by demonstration alleviates the complexity of robotic programming and allows extracting operator-specific knowledge in situ in a natural and intuitive way. The provision of incorporating force information can further improve the versatility of the system, allowing easy adaptation to different dynamic environments.

Keywords: Human and humanoid skills/cognition/interaction, Human-Robot Interaction, Learning from Demonstration
Abstract: In this paper we present a new approach for learning responsive robot behavior by imitation of human interaction partners. Extending previous work on robot imitation learning, that has so far mostly concentrated on learning from demonstrations by a single actor, we simultaneously record the movements of two humans engaged in on-going interaction tasks and learn compact models of the interaction. Extracted interaction models can thereafter be used by a robot to engage in a similar interaction with a human partner. We present two algorithms for deriving interaction models from motion capture data as well as experimental results on a humanoid robot.

Attachments: Video Attachment
Keywords: Motion and Trajectory Generation, Learning and Adaptive Systems, Cellular and Modular Robots
Abstract: The design of efficient locomotion gaits for robots with many degrees of freedom is challenging and time consuming even if optimization techniques are applied. Control parameters can be found through optimization in two ways: (i) through online optimization where the performance of a robot is measured while trying different control parameters on the actual hardware and (ii) through offline optimization by simulating the robot's behavior with the help of models of the robot and its environment.

In this paper, we present a hybrid optimization method that combines the best properties of online and offline optimization to efficiently find locomotion gaits for arbitrary structures. In comparison to pure online optimization, both the number of experiments using robotic hardware as well as the total time required for finding efficient locomotion gaits get highly reduced by running the major part of the optimization process in simulation using a cluster of processors. The presented example shows that even for robots with a low number of degrees of freedom the time required for optimization can be reduced by a factor of 2.5 to 30, at least, depending on how extensive the search for optimized control parameters should be. Time for hardware experiments becomes minimal. More importantly, gaits that can possibly damage the robotic hardware can be filtered before being tried in hardware. Yet in contrast to pure offline optimization, we reach well matched behavior that allows a direct transfer of locomotion gaits from simulation to hardware. This is because through a meta-optimization we adapt not only the locomotion parameters but also the parameters for simulation models of the robot and environment allowing for a good matching of the robot behavior in simulation and hardware.

We validate the proposed hybrid optimization method on a structure composed of two Roombots modules with a total number of six degrees of freedom. Roombots are self-reconfigurable modular robots that can form arbitrary structures with many degrees of freedom through an integrated active connection mechanism.

Attachments: Video Attachment
Keywords: Biologically-Inspired Robots, Biomimetics, Distributed Robot Systems
Abstract: Snakes are able to move effectively by using terrain irregularities as scaffolds against which they push their bodies. This locomotion is attractive from a robotic viewpoint because irregularities in the environment of conventional robots interfere with their operation. In a previous work, we proposed a decentralized control mechanism of the scaffold-based locomotion of snakes, which combined curvature derivative control with local pressure reflex. Here, we practically demonstrate how a snake-like robot utilizing the proposed control scheme moves effectively by pushing its body against pegs.

Keywords: Biologically-Inspired Robots, Joint/Mechanism, Mechanism Design
Abstract: Numerous snake-like robot mechanisms have been developed over the past several decades. A well studied kinematic structure consists of a series of segments coupled with rotational joints. In some designs, each segment is coupled with a 2-DOF joint. In others, segments are coupled through 1-DOF joints, with even numbered joints implementing roll and odd numbered segments implementing pitch. In this paper, we present a robotic snake that implements both rotational and translational degrees of freedom in each joint. This new design allows for several new gaits to be implemented. We begin by presenting the mechanical design of the robot, and derive the kinematic equations of the robot's joints. Next, the electrical and communication systems are described. Finally, several gaits unique to this kinematic design are demonstrated.

Attachments: Video Attachment
Keywords: Biologically-Inspired Robots, Redundant Robots, Motion Control
Abstract: This paper proposes a snake robot control method for climbing and descending a step. On a multi-plane step environment, it is necessary for locomotion to transfer from one plane to another. A snake robot can move with touching several planes as its body is long and thin. In this paper, we propose a control method for accomplishing trajectory tracking of a snake robot on a step environment. The control method is consist of the tracking controller, the shifting method of the robot's part connecting between the planes, and the active lifting for controlling the shape of the robot. Simulations and experiments demonstrated the effectiveness of the proposed controller and the shifting method of the connecting part of the robot's body.

Attachments: Video Attachment
Keywords: Education Robotics, Biologically-Inspired Robots, Entertainment Robotics
Abstract: In this paper, two types of biologically inspired educational robots based on gliding locomotion are presented. Gliding locomotion utilizes the difference between two orthogonal reaction forces to propel. Since this locomotion principle is very interesting and difficult to intuitively understand, its way of locomotion effectively evoke intellectual curiosity of students. One actuated degree of freedom (DOF) fish-like educational robot and its lecture program are developed for primary, junior high and high school students. And a snake-like educational robot which can connect arbitrary number of units, and its lecture program are developed for university students. We carried out these programs through several lectures. The results are also discussed in this paper.

Attachments: Video Attachment
Keywords: Biomimetics, Biologically-Inspired Robots
Abstract: This paper describes the development of an inspection robot for use in 1-inch gas pipes. These pipes are commonly used in residences and between gas meters and a main pipe that is buried under the road, and they require regular inspection. However, appropriately advanced inspection technologies have not yet been developed. An endoscope, which is the current inspection method, can only be utilized in a limited inspection scenarios. As for robot inspection, current in-pipe robots cannot pass through a 90-degree elbow, which has a radius of curvature equal to its inside diameter (Rc = 1.0 ID). However these elbows are frequently encountered in real-life environments. In this study, to solve these problems, we developed a peristaltic crawling robot with pneumatic artificial muscles for use in 1-inch gas pipes. This robot can pass through a 90-degree elbow (Rc = 1.0 ID) in the horizontal and vertical planes. In addition, this robot can be equipped with an endoscope and take videos inside a pipe. However, has been unable to pass through continuous elbows, which are occasionally encountered. For use in real-life environments, a robot is needed that can pass through continuous elbows. In this paper, we report the development of a robot that can pass through continuous elbows.

Keywords: Planning, Scheduling and Coordination, Multi-Robot Coordination, Distributed Robot Systems
Abstract: Many groups of agents exhibit emergent collective behaviors. The environment in which the agents operate is one determinant of the resulting behaviors. This work shows how automatic enumeration of environments enables exploration of various collective behaviors that perform useful group functions (e.g. segregation, corralling, shape formation). Although groups of agents, such as mobile robots, can be manipulated through explicit control, this study shows that these systems can be use- fully manipulated without resorting to such imperative means. This method has obvious uses for heterogeneous robot systems, especially those which include large numbers of simple agents. The method introduced is general, in that it takes as input: (1) algorithmic specifications of the environment generation, (2) a black-box model of the individual agent’s control laws, and (3) a mathematical description of the task objective. To show the validity of the proposed method this investigation studies two behaviors (splitting and corralling) for three commonly studied motion models, including the well known Reynold’s model. Simulations and physical multi-robot trials show that automatically generated environments can elicit pre-specified behaviors from a group of individual agents. Additionally, this work investigates the effects of a group’s emergent properties on the ability to elicit the specified behavior via the environment. The findings suggest that automatically exploring environments can lead to better exploration and understanding of collective behaviors, including the identification of previously unknown emergent behaviors.

Keywords: Planning, Scheduling and Coordination, Distributed Robot Systems, Biomimetics
Abstract: We introduce the concept of Maximum Sus- tainable Yield (MSY) to the context of autonomous robot foraging. MSY is an optimal approach to the problem of maximizing sustainable foraging where the resources harvested are replenished by logistic growth, e.g. living things. Over- harvesting reduces both the instantaneous resource availability and growth rate, and above some threshold will permanently deplete resources. Under-harvesting is sustainable, but fails to maximally exploit the resources. We describe a system model and use it to determine the optimal allocation of robot work to resource-producing ‘patches’. We give a practical illustration of a troublesome feature of MSY: it is too sensitive for a fixed allocation to be sustainable in practice. We show how to centrally allocate a number of robots to each patch, and then locally adapt the work rate of each robot to achieve sustainable and near-optimal foraging. This is the first study of robot foraging where the robots’ activity modifies the productivity and sustainability of the environment.

Attachments: Video Attachment
Keywords: Path Planning for Multiple Mobile Robots or Agents, Biologically-Inspired Robots, Motion and Path Planning
Abstract: Biological robots can be produced in large numbers, but are often controlled by uniform inputs. This makes position control of multiple robots inherently challenging.

This paper uses magnetically-steered ciliate eukaryon (Tetrahymena pyriformis) as a case study. These cells swim at a constant speed, and can be turned by changing the orientation of an external magnetic field. We show that it is possible to steer multiple T. pyriformis to independent goals if their turning---modeled as a first-order system---has unique time constants. We provide system identification tools to parameterize multiple cells in parallel.

We construct feedback control-Lyapunov methods that exploit differing phase-lags under a rotating magnetic field to steer multiple cells to independent target positions. We prove that these techniques scale to any number of cells with unique first-order responses to the global magnetic field. We provide simulations steering hundreds of cells and validate our procedure in hardware experiments with multiple cells.

Keywords: Planning, Scheduling and Coordination, Field Robots, Task Planning
Abstract: This paper introduces two objective functions for computing the expected cost in the Stochastic Collection and Replenishment (SCAR) scenario. In the SCAR scenario, multiple user agents have a limited supply of a resource that they either use or collect, depending on the scenario. To enable persistent autonomy, dedicated replenishment agents travel to the user agents and replenish or collect their supply of the resource, thus allowing them to operate indefinitely in the field. Of the two objective functions, one uses a Monte Carlo method, while the other uses a significantly faster analytical method. Approximations to multiplication, division and inversion of Gaussian distributed variables are used to facilitate propagation of probability distributions in the analytical method when Gaussian distributed parameters are used. The analytical objective function is shown to have greater than 99% comparison accuracy when compared with the Monte Carlo objective function while achieving speed gains of several orders of magnitude.

Attachments: Video Attachment
Keywords: Navigation, Autonomous Agents
Abstract: Path finding is a fundamental, yet computationally expensive problem in robotics navigation. Often times, it is necessary to sacrifice optimality to find a feasible plan given a time constraint due to the search complexity. Dynamic environments may further invalidate current computed plans, requiring an efficient planning strategy that can repair existing solutions. This paper presents a massively parallelized wavefront-based approach to path planning, running on the GPU, that can efficiently repair plans to accommodate world changes and agent movement, without having to restart the wavefront propagation process. In addition, we introduce a termination condition which ensures the minimum number of GPU iterations while maintaining strict optimality constraints on search graphs with non-uniform costs.

Attachments: Video Attachment
Keywords: Path Planning for Multiple Mobile Robots or Agents, Motion and Path Planning, Micro/Nano Robots
Abstract: In this paper we investigate controlling many nonholonomic unicycles that each receive exactly the same inputs. The robots are almost homogeneous, but each robot has a unique parameter that scales its turning rate. Previous work showed that such a collection of robots can be approximately steered to arbitrary Cartesian positions, but not to arbitrary heading angles in a global reference frame. We extend this work by proving we can always steer such a collection of robots exactly to arbitrary range and bearing locations relative to targets in R² in a finite number of steps. We also provide existence proofs for controlling the final heading angles of many robots. This work addresses a fundamental challenge in micro- and nanorobotics with possible applications in targeted therapy, sensing, and actuation. Scale hardware experiments validate the control policy. All code is provided online.

Keywords: Marine Robotics, Mapping
Abstract: This paper presents recent developments in data processing of multi-year repeat survey imagery and precision automatic registration for monitoring long-term changes in benthic marine habitats such as coral reefs and kelp forests. Three different methods are presented and compared for precision alignment of imagery maps collected over a range of time-scales from 12 hours to two years between dives. The first method uses Scale Invariant Feature Transform (SIFT) features computed over imagery mosaics to compute the relative translational offset between repeat dives. The second method employs scan-optimisation using the bathymetry generated via structure-from-motion thus capturing more stable features in the environment, lending itself to larger timescale registration. The third method uses mutual information optimisation to register imagery maps, providing robustness to changes in the colour and brightness of objects in an underwater scene across multiple years. Results are presented from field data collected using an Autonomous Underwater Vehicle (AUV) in sites across the Australian coast between 2009 and 2011.

Keywords: Marine Robotics, SLAM, Computer Vision
Abstract: This work presents a method for underwater stereo localization and mapping for detailed inspection tasks. The method generates dense, geometrically accurate reconstructions of underwater environments by compensating for image distortions due to refraction. A refractive model of the camera and enclosure is calculated offline using calibration images and produces non-linear epipolar curves for use in stereo matching. An efficient block matching algorithm traverses the precalculated epipolar curves to find pixel correspondences and depths are calculated using pixel ray tracing. Finally the depth maps are used to perform dense simultaneous localization and mapping to generate a 3D model of the environment. The localization and mapping algorithm incorporates refraction corrected ray tracing to improve map quality. The method is shown to improve overall depth map quality over existing methods and to generate high quality 3-D reconstructions.

Keywords: Marine Robotics, Localization, Sensor Networks
Abstract: The effect of ocean flow on the motion of autonomous underwater vehicles (AUV) is often crucial in the development of underwater localization algorithms and should not be treated as small disturbances. The domination of strong ocean currents and the requirement of low power consumption prohibit AUVs to move against a background flow to obtain localization correction in a timely manner. Our recent studies, among others, enable an unmanned vehicle to follow a near optimal trajectory found by Lagrangian coherent structures based fluid control algorithm with minimal fuel usage, which improves the vehicles' runtime and the path following accuracy in the presence of strong background flow. Here, we propose a three-dimensional fully distributed localization hierarchy to improve the localization of low-cost mobile marine data collection underwater sensor networks using intra-vehicle communication and measurements. The proposed algorithm is realized by using the extended Kalman filter. Correlation terms in covariance matrices are considered independently to meet the distributed feature. Resulting simulated localization errors are bounded at satisfactory levels and the relationship between the number of AUVs and the performance of the algorithm is investigated.

Keywords: Marine Robotics, Learning and Adaptive Systems, Energy and environment monitoring and management
Abstract: Robotic vehicles have become a critical tool for studying the under-sampled coastal ocean. This has led to new paradigms in scientific discovery. The combination of agility, reactivity, and persistent presence makes autonomous robots ideal for targeted sampling of elusive, episodic events such as algal blooms. In order to achieve this goal, they need to be deployed at the right place and time. To that end, we have designed and will soon deploy a shore-based event recognition technology to continuously monitor remote sensing imagery for algal blooms as targets for robotic field experiments. A Support Vector Machine underlies a field-tested decision support system which scientists will consult prior to deploying robots in the coastal ocean. Our initial experiments targeted for the Monterey Bay will be extended for the upcoming March 2013 field experiments in the Southern California Bight.

Keywords: Marine Robotics, Networked Robots, Learning and Adaptive Systems
Abstract: Underwater acoustic communication channels display highly variable and stochastic performance, especially in multipath-limited shallow-water and harbor environments. A mobile acoustic node can, however, learn about the channel's properties as it moves about. Maximizing the cumulative data transmission through adaptive node positioning is in fact a clean exploitation vs. exploration scenario because we trade off learning about poorly known locations with exploiting good ones. While this problem is well described with the stochastic multi-armed bandit formalism, the classical assumption of costless switching is untenable in the field, where slow-moving vehicles are covering large distances. We present a heuristic adaptation to the MAB Gittins index rule with limited policy enumeration to account for switching costs, and describe field experiments conducted in the Charles River (Boston MA). The field data establish that the MAB and its switching cost extension are tractable in this application, and that performance is consistently superior to that of epsilon-greedy policies.

Keywords: Marine Robotics, Networked Robots, Multi-Robot Coordination
Abstract: We make two contributions toward integrated monitoring over large spatial scales, with multiple collaborating vehicles. Our focus is dynamic ocean features such as fronts and plumes. To support strong networked-control designs, we first develop a clean linear time-invariant framework for tracking features, that directly couples the global structure of the process to vehicle positioning. To address the packet loss inherent in underwater acoustic communications, we then extend the synthesis technique of Imer et al. [1] to the case where measurements and control commands suffer loss with differing statistics among the multiple channels. Simulations show that the integrated feedback system achieves good performance in front tracking.

Attachments: Video Attachment
Keywords: Motion Control, Industrial Robots, Biologically-Inspired Robots
Abstract: The common view on feedforward control is that it needs an accurate model in order to accurately predict a future state of the system. However, in this paper we show that there are model inaccuracies that do not affect the final position of a motion, when using the right feedforward controller. Having an accurate final position is the main requirement in the task we consider: a pick-and-place task. We optimized the feedforward controllers such that the effect of model inaccuracies on the final position was minimized. The system we studied is a one DOF robotic arm in the horizontal plane, of which we show simulation and hardware results. The results show that the errors in the final position can be reduced to approximately zero for an inaccurate Coulomb, viscous or torque dependent friction. Furthermore, errors in the final position can be reduced, but not to zero, for an inaccurate inertia or motor constant. In conclusion, we show that for certain model inaccuracies, no feedback is required to eliminate the effect of an inaccurate model on the final position of a motion.

Attachments: Video Attachment
Keywords: Motion Control, Legged Robots, Kinematics
Abstract: We present a general approach to design modular controllers for limit cycle locomotion over unperceived rough terrain. The control strategy uses a Central Pattern Generator (CPG) model implemented as coupled nonlinear oscillators as basis. Stumbling correction and leg extension reflexes are implemented as feedbacks for fast corrections, and model based posture control mechanisms define feedbacks for continuous corrections. The control strategy is validated on a detailed physics-based simulated model of a compliant quadruped robot, the Oncilla robot. We demonstrate dynamic locomotion with a speed of more than 1.5 BodyLength/s over unperceived uneven terrains, steps, and slopes.