Keywords: Motion and Trajectory Generation, Mapping, Domestic Robots and Home Automation
Abstract: We address the problem of systematically covering all accessible space of an unknown environment by a mobile robot. Our approach uses rectangular regions that are swept over the environment. The robot covers each region using the classic boustrephedon pattern and planning paths to uncovered areas within the region while keeping track of its position uncertainty. The region is then moved sideways for covering the next part of the environment until all accessible space has been visited. In a second stage the robot revisits the perimeter around obstacles. We compare our method to 5 off-line methods including the distance transformation by Zelinsky et al. [1] in a standard test environment as well as in multi-bedroom homes. The presented method can be employed in our Mint cleaning robot for autonomously sweeping and mopping floors.

Keywords: SLAM
Abstract: Efficiently solving large-scale sparse linear systems is important for robot mapping and navigation. Recently, the subgraph-preconditioned conjugate gradient method has been proposed to combine the advantages of two reigning paradigms, direct and iterative methods, to improve the efficiency of the solver. Yet the question of how to pick a good subgraph is still an open problem. In this paper, we propose a new metric to measure the quality of a spanning tree preconditioner based on support theory. We use this metric to develop an algorithm to find good subgraph preconditioners and apply them to solve the SLAM problem. The results show that although the proposed algorithm is not fast enough, the new metric is effective and resulting subgraph preconditioners significantly improve the efficiency of the state-of-the-art solver.

Keywords: SLAM, Mapping, Localization
Abstract: Graphical models jointly with non linear optimization have become the most popular approaches for solving SLAM and Bundle Adjustment problems: using a non linear least squares (NLSQs) description of the problem, these math tools serve to formalize the minimization of an error cost function that relates state variables through relative sensor observations. The simplest case just considers as state variables the locations of the sensor/robot in the environment deriving in a pose graph subproblem. In general, the cost function is based on the L_2 norm whose principal iterative solutions exploit the sparse connectivity of the corresponding Gaussian Markov Field (GMRF) or the Factor Graph, whose adjacency matrices are given by the fill-in of the Hessian and Jacobian of the cost function respectively.

In this paper we propose a novel solution based on the L_1 norm as a back-end to the pose graph subproblem. In contrast to other NLSQs approaches, we formulate an iterative algorithm inspired directly on the Factor Graph structure to solve for the linearized residual |Ax-b|_1. Although the results obtained when spurious measurements are present is similar to the robust Huber norm, our main interest in L_1 optimization is that it opens the door to more robust non-convex L_p norms where p <= 1. Since our approach depends on the minimization of a non differentiable function, we provide the theoretical insights to solve for the L_1 norm. Our optimization is based on a primal-dual formulation successfully applied for solving variational convex problems in computer vision. We show the effectiveness of the L_1 norm to produce both a robust initial seed and a final optimized solution on challenging and well known datasets widely used in other state of the art works.

Keywords: SLAM, Mapping, Localization
Abstract: This paper presents a strategy for large-scale SLAM through solving a sequence of linear least squares problems. The algorithm is based on submap joining where submaps are built using any existing SLAM technique. It is demonstrated that if submaps coordinate frames are judiciously selected, the least squares objective function for joining two submaps becomes a quadratic function of the state vector. Therefore, a linear solution to large-scale SLAM that requires joining a number of local submaps either sequentially or in a more efficient Divide and Conquer manner, can be obtained. The proposed Linear SLAM technique is applicable to both feature-based and pose graph SLAM, in two and three dimensions, and does not require any assumption on the character of the covariance matrices or an initial guess of the state vector. Although this algorithm is an approximation to the optimal full nonlinear least squares SLAM, simulations and experiments using publicly available datasets in 2D and 3D show that Linear SLAM produces results that are very close to the best solutions that can be obtained using full nonlinear optimization started from an accurate initial value. The C/C++ and MATLAB source codes for the proposed algorithm are available on OpenSLAM.

Keywords: SLAM
Abstract: Simultaneous Localization and Mapping (SLAM) is one of the most difficult tasks in mobile robotics. While the construction of consistent and coherent local solutions is simple, the SLAM remains a critical problem as the distance travelled by the robot increases. To circumvent this limitation, many strategies divide the environment in small regions, and formulate the SLAM problem as a combination of multiple precise submaps. In this paper, we propose a new submap-based particle filter algorithm called Segmented DP-SLAM, that combines an optimized data structure to store the maps of the particles with a probabilistic map of segments, representing hypothesis of submaps topologies. We evaluate our method through experimental results obtained in simulated and real environments.

Keywords: SLAM
Abstract: In the state-of-the-art approaches to SLAM, the problem is often formulated as a non-linear least squares. SLAM back-ends often employ iterative methods such as Gauss-Newton or Levenberg-Marquardt to solve that problem. In general, there is no guarantee on the global convergence of these methods. The back-end might get trapped into a local minimum or even diverge depending on how good the initial estimate is. Due to the large noise in odometry data, it is not wise to rely on dead reckoning for obtaining an initial guess, especially in long trajectories. In this paper we demonstrate how M-estimation can be used as a bootstrapping technique to obtain a reliable initial guess. We show that this initial guess is more likely to be in the basin of attraction of the global minimum than existing bootstrapping methods. As the main contribution of this paper, we present new insights about the similarities between robustness against outliers and robustness against a bad initial guess. Through simulations and experiments on real data, we substantiate the reliability of our proposed method.

Attachments: Video Attachment
Keywords: Visual Servoing, Visual Tracking, Industrial Robots
Abstract: This paper presents high speed and high accuracy visual servoing system. The algorithm has three major improvements, which can be implemented in practical applications; First pose estimation under rough calibration, second real time implementation issues with non-real-time image processing hardware and third a consideration for industrial positioncontroller. To resolve the issues, position-based visual servoing PBVS) is adopted and appearance model-based virtual visual servoing (VVS) is applied for position estimation. VVS approach does not compute the stereo matching but directly compares the OpenGL rendered image and camera image for each camera; estimate the position/orientation using VVS independently for each camera; and provides a theoretically optimal compromise among those estimates under inaccurate camera calibration. To enhance estimation accuracy, a hybrid method of stereo trigonometry for position estimation and weighted least squares for the orientation estimation is proposed in combination with the information from the stereo cameras. Operation speed is enhanced by using graphic processing unit (GPU) acceleration and an on-line trajectory generator which can accommodate the variable cycle of the visual servoing and the fixed cycle of a common robot controller. Finally, some experimental results illustrate the effectiveness of the proposed framework.

Attachments: Video Attachment
Keywords: Visual Servoing, Collision Detection and Avoidance, Aerial Robotics
Abstract: This paper presents practical vision-based collision avoidance for objects approximating a single point feature. Using a spherical camera model, a visual predictive control scheme guides the aircraft around the object along a conical spiral trajectory. Visibility, state and control constraints are considered explicitly in the controller design by combining image and vehicle dynamics in the process model, and solving the nonlinear optimization problem over the resulting state space. Importantly, range is not required. Instead, the principles of conical spiral motion are used to design an objective function that simultaneously guides the aircraft along the avoidance trajectory, whilst providing an indication of the appropriate point to stop the spiral behaviour. Our approach is aimed at providing a potential solution to the See and Avoid problem for unmanned aircraft and is demonstrated through a series of experimental results using a small quadrotor platform.

Attachments: Video Attachment
Keywords: Visual Servoing
Abstract: Aim at enhancing dexterous and safe operation in unstructured environment, a cable-driven soft robotic manipulator is designed in this paper. Due to soft material it made of and nearly infinite degree of freedom it owns, the soft robotic manipulator has higher security and dexterity than traditional rigid-link manipulator, which make it suitable to perform tasks in complex environments that is narrow, confined and unstructured. Though the soft robotic manipulator possesses advantages above, it is not an easy thing for it to achieve precise position control. In order to solve this problem, a kinematic model based on piecewise constant curvature hypothesis is proposed. Through building up three spaces and two mappings, the relationship between the length variables of 4 cables and the position and orientation of the soft robotic manipulator end-effector is obtained. Afterwards, a depth-independent image Jacobian matrix is introduced and an image-based visual servo controller is presented. Applied by adaptive algorithm, the controller could estimate unknown position of the feature point online, and then Lyapunov theory is used to prove the stability of the proposed controller. At last, experiments are conducted to demonstrate rationality and validity of the kinematic model and adaptive visual servo controller.

Keywords: Visual Servoing
Abstract: This paper introduces a new comprehensive solution for the open problem of uncalibrated 3D image-based stereo visual servoing for robot manipulators. One of the main contributions of this article is a novel 3D stereo camera model to map positions in the task space to positions in a new 3D Visual Cartesian Space (a visual feature space where 3D positions are measured in pixel). This model is used to compute a full-rank Image Jacobian Matrix(Jimg), which solves several common problems presented on the classical image Jacobians, e.g., image space singularities and local minima. This Jacobian is a fundamental key for the image-based control design, where uncalibrated stereo camera systems can be used to drive a robot manipulator. Furthermore, an adaptive second order sliding mode visual servo control is designed to track 3D visual motions using the 3D trajectory errors defined in the Visual Cartesian Space. The stability of the control in closed loop with a dynamic robot system is formally analyzed and proved, where exponential convergence of errors in the Visual Cartesian Space and task space without local minima are demonstrated. The complete control system is evaluated both in simulation and on a real industrial robot. The robustness of the control scheme is evaluated for cases where the extrinsic parameters of the stereo camera system change on-line and the kinematic/dynamic robot parameters are considered as unknown. This approach offers a proper solution for the common problem of visual occlusion, since the stereo system can be moved to obtain a clear view of the task at any time.

Keywords: Visual Servoing, Visual Tracking, Computer Vision
Abstract: This article addresses the problem of direct vision-based robot control where the equilibrium state is defined via a reference image. Direct methods refer to intensity-based nonmetric techniques to perform that stabilization. Intensity-based strategies provide for higher accuracy, whereas not requiring any metric information improves their versatility. However, existing direct techniques either have a coupled error dynamics, or are designed for planar objects only. This paper proposes a new direct technique that decouples the translational motion from the rotational one for the general case of both planar and nonplanar targets under general translational and rotational displacements. Furthermore, for the important case of a fronto-parallel planar object, the proposed technique leads to a fully diagonal interaction matrix. The equilibrium state is made locally exponentially stable for all those cases. These improvements are theoretically proven and experimentally demonstrated using a 6-DoF robotic arm.

Attachments: Video Attachment
Keywords: Visual Servoing, Visual Tracking
Abstract: We present a new image-based visual servoing scheme for tracking moving targets. This is achieved with a twofold approach. First, we devise a straightforward adaptation of a previously proposed depth observer to account for the fact that the target is not stationary. Second, we estimate the disturbance on the visual feature dynamics due to the target motion, and we add a related compensation term to the visual controller. In particular, the target velocity components parallel to the image plane are reconstructed using a disturbance observer, whereas the orthogonal component is retrieved from the measurement of the Focus Of Expansion. Comparative experiments show that the proposed method can improve over classical visual servoing schemes by 50% or more.

Keywords: Recognition, Learning and Adaptive Systems
Abstract: On-the-fly learning systems are necessary for the deployment of general purpose robots. New training examples for such systems are often supplied by mentor interactions. Due to the cost of acquiring such examples, it is desirable to reduce the number of necessary interactions. Transfer learning has been shown to improve classification results for classes with small numbers of training examples by pooling knowledge from related classes. Standard practice in these works is to assume that the relationship between the transfer target and related classes is already known.

In this work, we explore how previously learned categories, or related groupings of classes, can be used to transfer knowledge to novel classes without explicitly known relationships to them. We demonstrate an algorithm for determining the category membership of a novel class, focusing on the difficult case when few training examples are available. We show that classifiers trained via this method outperform classifiers optimized to learn the novel class individually when evaluated on both synthetic and real-world datasets.

Keywords: Human and humanoid skills/cognition/interaction, Medical Robots and Systems, Contact Modelling
Abstract: This paper proposes a method for vascular load reduction control that operates in regard to the load on contact points of catheter and blood vessels in catheter insertion. We make an extracorporeal estimation of the load on the contact points, and perform control with a robot arm to reduce the estimated load. We aim to reduce the vascular load through extracting and vibrating action as actually applied by operators. In order to confirm the effectiveness of the proposed method, we conduct an evaluation experiment where a wire is inserted in a tube that simulates a blood vessel. As a result of the experiment we were able to estimate the force on the contact points with an accuracy of an estimation error of 0.0531[N]. Moreover, through vibration control we were able to reduce the load to below 0.1[N] for places where there was an overload of more than 0.5[N]. For vibration control, the experiment also enabled us to derive an effective parameter adjustment method to remove obstructions.

Keywords: Human and humanoid skills/cognition/interaction, Humanoid Robots, Dynamics
Abstract: This paper proposes an identification technique of a human standing controller. The dynamics of a human is approximated by the macroscopic relationship between the center of mass and the zero-moment point. The standing controller is modelled by a piecewise-linear feedback, which was originally developed for humanoid robots. In the previous work, the authors found a qualitative similarity of the model to an actual human behavior observed in a phase space, and the next challenge was to identify the controller from those data. A difficulty is that the observed dynamics is a piecewise system due to the unilaterality of reaction forces, so that the identification is not straightforward. It is not trivial how to detect the switching point in each motion locus and how to find the trust region of the supposed model. The recursive-least-square (RLS) method, which can present the deviation of identified parameters and that of the reliability of the results, helps to estimate the trust region with a returning computation process. Through the identification, the validity of the proposed method was verified. More study about the availability of the COM-ZMP model and the piecewise-linear controller for the analyses of the human standing control is also reported.

Keywords: Virtual Reality and Interfaces, Learning from Demonstration, AI Reasoning Methods
Abstract: Teaching robots everyday tasks like making pancakes by instructions requires interfaces that can be intuitively operated by non-experts. By performing novel manipulation tasks in a virtual environment using a data glove task-related information of the demonstrated actions can directly be accessed and extracted from the simulator. We translate low-level data structures of these simulations into meaningful first-order representations whereby we are able to select data segments and analyze them at an abstract level. Hence, the proposed system is a powerful tool for acquiring examples of manipulation actions and for analyzing them whereby robots can be informed how to perform a task.

Attachments: Video Attachment
Keywords: Behaviour-Based Systems, Autonomous Agents, Human and humanoid skills/cognition/interaction
Abstract: To achieve a certain task, a skilligent robot should be able to learn the skills embedded in that task. Furthermore, the robot should be able to infer such skills to handle uncertainties and perturbations, since most robot tasks are usually daily-life tasks that include many unexpected situations. Therefore, we propose a unified skill learning and inference framework. The framework includes six processing modules: 1) a human demonstration process, 2) an autonomous segmentation process, 3) a dynamic movement primitive learning process, 4) a Bayesian network learning process, 5) a motivation graph construction process, and 6) a skill-inferring process. Based on the framework, the robot learns and infers situation-adequate and goal-oriented skills to handle uncertainties and human perturbations. To show the validity of our framework, some experimental results are illustrated using a robot arm that performs a 'tea service' task.

Attachments: Video Attachment
Keywords: Human-Robot Interaction, Robotics in Hazardous Fields, Haptics and Haptic Interfaces
Abstract: In the case of human intervention in disaster response operations like indoor firefighting, where the environment perception is limited due to thick smoke, noise in the oxygen masks and clutter, not only limit the environmental perception of the human responders, but also causes distress. An intelligent agent (man/machine) with full environment perceptual capabilities is an alternative to enhance navigation in such unfavorable environments. Since haptic communication is the least affected mode of communication in such cases, we consider human demonstrations to use a hard rein to guide blindfolded followers with auditory distraction to be a good paradigm to extract salient features of guiding using hard reins. Based on numerical simulations and experimental systems identification based on demonstrations from eight pairs of human subjects, we show that, the relationship between the orientation difference between the follower and the guider, and the lateral swing patterns of the hard rein by the guider can be explained by a novel 3 rd order auto regressive predictive controller. Moreover, by modeling the two party voluntary movement dynamics using a virtual damped inertial model, we were able to model the mutual trust between two parties. In the future, the novel controller extracted based on human demonstrations can be tested on a human-robot interaction scenario to guide a visually impaired person in various applications like fire fighting, search and rescue, medical surgery, etc.

Keywords: Robot Companions and Social Human-Robot Interaction, Gesture, Posture, Social Spaces and Facial Expressions, Performance Evaluation and Benchmarking
Abstract: We evaluated the effects of robot gaze behavior on interactions with multiple users in a museum-like setting. We posit that a robot needs to divide its attention between multiple users and may be able to use its gaze to ‘point’ at objects of interest. A 2 (person-oriented [only looking at participants] vs. object-oriented [also looking at artworks] gaze) x 2 (‘favored’ [looked at more] vs. ‘not favored’ [looked at less] by the robot) mixed factorial design (N=57) study was carried out in a museum-like lab setting where a robot talked about two artworks to groups of three participants. Results indicate that ‘favored’ participants did indeed pay more attention to the robot and the artworks. However, surprisingly they paid more attention when the robot did not look over to the object of interest compared to when it did give this gaze cue. The findings suggest that using an object-oriented gaze as a cue for people to look at an object may not carry across readily from person-to-person to human-robot communication. People had trouble interpreting the cue and were possibly distracted by the robot’s movement.

Attachments: Video Attachment
Keywords: Human-Humanoid Interaction, Cognitive Human-Robot Interaction, Human and humanoid skills/cognition/interaction
Abstract: Cooperation is at the core of human social life. In this context, two major challenges face research on human-robot interaction: the first is to understand the underlying structure of cooperation, and the second is to build, based on this understanding, artificial agents that can successfully and safely interact with humans. Here we take a psychologically grounded and human-centered approach that addresses these two challenges. We test the hypothesis that optimal cooperation between a naïve human and a robot requires that the robot can acquire and execute a joint plan, and that it communicates this joint plan through ecologically valid modalities including spoken language, gesture and gaze. We developed a cognitive system that comprises the human-like control of social actions, the ability to acquire and express shared plans and a spoken language stage. In order to test the psychological validity of our approach we tested 12 naïve subjects in a cooperative task with the robot. We experimentally manipulated the presence of a joint plan (vs. a solo plan), the use of task-oriented gaze and gestures, and the use of language accompanying the unfolding plan. The quality of cooperation was analyzed in terms of proper turn taking, collisions and cognitive errors. Results showed that while successful turn taking could take place in the absence of the explicit use of a joint plan, its presence yielded significantly greater success. One advantage of the solo plan was that the robot would always be ready to generate actions, and could thus adapt if the human intervened at the wrong time, whereas in the joint plan the robot expected the human to take his/her turn. Interestingly, when the robot represented the action as involving a joint plan, gaze provided a highly potent nonverbal cue that facilitated successful collaboration and reduced errors in the absence of verbal communication. These results support the cooperative stance in human social cognition, and suggest that cooperative robots should employ joint plans, fully communicate them in order to sustain effective collaboration while being ready to adapt if the human makes a midstream mistake.

Attachments: Video Attachment
Keywords: Human-Robot Interaction, Robot Companions and Social Human-Robot Interaction, Autonomous Agents
Abstract: We present a multimodal system for creating, modifying and commanding groups of robots from a population. Extending our previous work on selecting an individual robot from a population by face engagement, we show that we can dynamically create groups of a desired number of robots by speaking the number we desire, e.g. “You three”, and looking at the robots we intend to form the group. We evaluate two different methods of detecting which robots are intended by the user, and show that an iterated election performs well in our setting. We also show that teams can be modified by adding and removing individual robots: “And you. Not you”. The success of the system is examined for different spatial configurations of robots with respect to each other and the user to find the proper workspace of selection methods.

Keywords: Cognitive Human-Robot Interaction, Integrated Task and Motion Planning, Software and Architecture
Abstract: We present a methodology for enabling service robots to follow natural language commands from non-expert users, with and without user-specified constraints, with a particular focus on spatial language understanding. As part of our approach, we propose a novel extension to the semantic field model of spatial prepositions that enables the representation of dynamic spatial relations involving paths. The design, system modules, and implementation details of our robot software architecture are presented and the relevance of the proposed methodology to interactive instruction and task modification through the addition of constraints is discussed. The paper concludes with an evaluation of our robot software architecture implemented on a simulated mobile robot operating in both a 2D home environment and in real world environment maps to demonstrate the generalizability and usefulness of our approach in real world applications.

Keywords: Behaviour-Based Systems, Human-Robot Interaction, Recognition
Abstract: Motion recognition is an essential technology for social robots in various environments such as homes, offices and shopping center, where the robots are expected to understand human behavior and interact with them. In this paper, we present a system composed of three models: motion language model, natural language model and integration inference model, and achieved to generate sentences from motions using large high-order N-grams. We confirmed not only that using higher-order N-grams improves precision in generating long sentences but also that the computational complexity of the proposed system is almost the same as our previous one. In addition, we improved the precision by aligning the graph structure representing generated sentences into confusion network form. This means that simplifying and compacting word sequences affect the precision of sentence generation.

Keywords: Recognition, Visual Learning, Learning and Adaptive Systems
Abstract: In this study, we propose a method for concept formation and word acquisition for robots. The proposed method is based on multimodal latent Dirichlet allocation (MLDA) and the nested Pitman-Yor language model (NPYLM). A robot obtains haptic, visual, and auditory information by grasping, observing, and shaking an object. At the same time, a user teaches object features to the robot through speech, which is recognized using only acoustic models and transformed into phoneme sequences. As the robot is supposed to have no language model in advance, the recognized phoneme sequences include many phoneme recognition errors. Moreover, the recognized phoneme sequences with errors are segmented into words in an unsupervised manner; however, not all words are necessarily segmented correctly. The words including these errors have a negative effect on the learning of word meanings. To overcome this problem, we propose a method to improve unsupervised word segmentation and to reduce phoneme recognition errors by using multimodal object concepts. %To improve the unsupervised word segmentation, we use multimodal object concepts for segmenting the sentences. In the proposed method, object concepts are used to enhance the accuracy of word segmentation, reduce phoneme recognition errors, and correct words so as to improve the categorization accuracy. We experimentally demonstrate that the proposed method can improve the accuracy of word segmentation and reduce the phoneme recognition error and that the obtained words enhance the categorization accuracy.

Keywords: Learning and Adaptive Systems, Kinematics, Redundant Robots
Abstract: This paper presents a comparison of open-loop and closed-loop control strategies for tracking a task space trajectory, using redundant robots. We do not assume any knowledge of the analytical forward and inverse kinematics, relying instead on learning these models online, while executing a desired task. Specifically, we employ a recent learning algorithm that allows to learn a probabilistic model from which both the forward and inverse solutions can be obtained, as well as the Jacobian of the kinematics map. Such learned model can then be used to implement both types of control. Moreover, the multi-valued solutions provided by the learned model can be applied to redundant systems in which an infinite number of inverse solutions may exist. We present experiments with a simulated version of the iCub, a highly redundant humanoid robot, in which this learned model is employed to execute both open-loop and closed-loop trajectory control. We show the advantages and drawbacks of both control strategies, and we propose a way to combine them to deal with sensor noise and failures, showing the benefits of using a learning algorithm that can simultaneously provide forward and inverse predictions.

Keywords: Formal Methods in Robotics and Automation, Learning and Adaptive Systems, Collision Detection and Avoidance
Abstract: Given a stochastic policy learned by reinforcement, we wish to ensure that it can be deployed on a robot with demonstrably low probability of unsafe behavior. Our case study is about learning to reach target objects positioned close to obstacles, and ensuring a reasonably low collision probability. Learning is carried out in a simulator to avoid physical damage in the trial-and-error phase. Once a policy is learned, we analyze it with probabilistic model checking tools to identify and correct potential unsafe behaviors. The whole process is automated and, in principle, it can be integrated step-by-step with routine task-learning. As our results demonstrate, automated fixing of policies is both feasible and highly effective in bounding the probability of unsafe behaviors.

Attachments: Video Attachment
Keywords: Learning and Adaptive Systems, Visual Navigation, Adaptive Control
Abstract: This paper presents a path-repeating, mobile robot controller that combines a feedforward, proportional Iterative Learning Control (ILC) algorithm with a feedback-linearized path-tracking controller to reduce path-tracking errors over repeated traverses along a reference path. Localization for the controller is provided by an on-board, vision-based mapping and navigation system enabling operation in large-scale, GPS-denied, extreme environments. The paper presents experimental results including over 600 m of travel by a four-wheeled, 50 kg robot travelling through challenging terrain including steep hills and sandy turns and by a six-wheeled, 160 kg robot at gradually-increased speeds up to three times faster than the nominal, safe speed. In the absence of a global localization system, ILC is demonstrated to reduce path-tracking errors caused by unmodelled robot dynamics and terrain challenges.

Keywords: Learning and Adaptive Systems, Motion Control, Humanoid Robots
Abstract: Learning can be used to optimize robot motions to new situations. Learning motions can cause high frequency random motions in the exploration phase and can cause failure before the motion is learned. The mean time between failures (MTBF) of a robot can be predicted while it is performing these motions. The predicted MTBF in the exploration phase can be increased by filtering actions or possible actions of the algorithm. We investigated five algorithms that apply this filtering in various ways and compared them to SARSA(lambda) learning. In general, increasing the MTBF decreases the learning performance. Three of the investigated algorithms are unable to increase the MTBF while keeping their learning performance approximately equal to SARSA(lambda). Two algorithms are able to do this: the PADA algorithm and the low-pass filter algorithm. In case of LEO, a bipedal walking robot that tries to optimize a walking motion, the MTBF can be increased by a factor of 108 compared to SARSA(lambda). This indicates that, in some cases, failures due to high frequency random motions can be prevented without decreasing the performance.

Attachments: Video Attachment
Keywords: Learning and Adaptive Systems, Legged Robots, Motion Control
Abstract: This paper presents the application of reinforcement learning to improve the performance of highly dynamic single legged locomotion with compliant series elastic actuators. The goal is to optimally exploit the capabilities of the hardware in terms of maximum jump height, jump distance, and energy efficiency of periodic hopping. These challenges are tackled with the reinforcement learning method Policy Improvement with Path Integrals (PI²) in a model-free approach to learn parameterized motor velocity trajectories as well as high-level control parameters. The combination of simulation and hardware-based optimization allows to efficiently obtain optimal control policies in an up to 10-dimensional parameter space. The robotic leg learns to temporarily store energy in the elastic elements of the joints in order to improve the jump height and distance. In addition, we present a method to learn time-independent control policies and apply it to improve the energetic efficiency of periodic hopping.

Attachments: Video Attachment
Keywords: Learning and Adaptive Systems, Legged Robots, Sensor Fusion
Abstract: In this paper we present a framework to learn a model-free feedback controller for locomotion and balance control of a compliant quadruped robot walking on rough terrain. Having designed an open-loop gait encoded in a Central Pattern Generator (CPG), we use a neural network to represent sensory feedback inside the CPG dynamics. This neural network accepts sensory inputs from a gyroscope or a camera, and its weights are learned using Particle Swarm Optimization (unsupervised learning). We show with a simulated compliant quadruped robot that our controller can perform significantly better than the open-loop one on slopes and randomized height maps.

Attachments: Video Attachment
Keywords: Integrated Task and Motion Planning, Task Planning, Manipulation Planning and Control
Abstract: Robot task planning is an inherently challenging problem, as it covers both continuous-space geometric reasoning about robot motion and perception, as well as purely symbolic knowledge about actions and objects. This paper presents a novel "knowledge of volumes" framework for solving generic robot tasks in partially known environments. In particular, this approach (abbreviated, KVP) combines the power of symbolic, knowledge-level AI planning with the efficient computation of volumes, which serve as an intermediate representation for both robot action and perception. While we demonstrate the effectiveness of our framework in a bimanual robot bartender scenario, our approach is also more generally applicable to tasks in automation and mobile manipulation, involving arbitrary numbers of manipulators.

Keywords: Integrated Task and Motion Planning, Task Planning, Autonomous Agents
Abstract: Autonomous vehicles (or drones) are very frequently used for servicing a geographic region in numerous applications. Given a geographic territory and a set of n fixed vehicle depots, we consider the problem of designing service districts so as to balance the workload of a collection of vehicles which service this region. We assume that the territory is a connected polygonal region, i.e. a simply connected polygon containing a set of simply connected obstacles. We give a fast algorithm, based on an infinite-dimensional optimization formulation, that divides the territory into compact, connected sub-regions, each of which contains a vehicle depot, such that all regions have equal area. We also show how we can use this algorithm to find better locations of the vehicle depots.

Keywords: Task Planning, Planning, Scheduling and Coordination, Industrial Robots
Abstract: Production speed and energy efficiency are crucial factors for any application scenario in industrial robotics. The most important factor for this is planning of an optimized sequence of atomic subtasks. In a welding scenario, an atomic subtask could be understood as a single welding seam/spot while the sequence could be the ordering of these atomic tasks. Optimization of a task sequence is normally modeled as the Traveling Salesman Problem (TSP). This works well for simple scenarios with atomic tasks without execution freedom like spot welding. However, many types of tasks allow a certain freedom of execution. A simple example is seam welding of a closed-contour, where typically the starting-ending point is not specified by the application. This extra degree of freedom allows for much more efficient task sequencing. In this paper, we describe an extension of TSP to model a problem of finding an optimal sequence of tasks with such extra degree of freedom. We propose a new, efficient heuristic to solve such problems and show its applicability. Obtained computational results are close to the optimum on small instances and outperforms the state of the art approaches on benchmarks available in literature.

Attachments: Video Attachment
Keywords: Integrated Task and Motion Planning, AI Reasoning Methods, Mobile Manipulation
Abstract: We present a hierarchical planning and execution architecture that maintains the computational efficiency of hierarchical decomposition while improving optimality. It provides mechanisms for monitoring the belief state during execution and performing selective replanning to repair poor choices and take advantage of new opportunities. It also provides mechanisms for looking ahead into future plans to avoid making short-sighted choices. The effectiveness of this mechanism is shown through comparative experiments in simulation and demonstrated on a real PR2 robot.

Keywords: Integrated Task and Motion Planning, Task Planning
Abstract: While symbolic planners work with an abstract representation of the real world, allowing plans to be constructed relatively quickly, geometric planning—although more computationally complex—is essential for building symbolic plans that actually work in the real world. To combine the two types of systems, we present in this paper a meaningful interface, and insights into a methodology for developing interwoven symbolic-geometric domains. We concretely present this “link” between the two approaches with algorithms and data structures that amount to an intermediate layer that coordinates symbolic-geometric planning. Since both planners are capable of “backtracking” at their own levels, we also investigate the issue of how to interleave their backtracking, which we do in the context of the algorithms that form the link. Finally, we present a prototype implementation of the combined system on a PR2 robot.

Keywords: Integrated Task and Motion Planning, Behaviour-Based Systems, Integrated Planning and Control
Abstract: We propose a novel framework to combine model-checking-based motion planning with action planning using action description languages, aiming to tackle task specifications given as Linear Temporal Logic (LTL) formulas. The specifications implicitly require both sequential regions to visit and the desired actions to perform at these regions. The robot's motion is abstracted based on sphere regions of interest in the workspace and the structure of navigation function(NF)-based controllers, while the robot's action map is constructed based on precondition and effect functions associated with the actions. An optimal planner is designed that generates the discrete motion-and-action plan fulfilling the specification, as well as the low-level hybrid controllers that implement this plan. The whole framework is demonstrated by a case study.

Keywords: Field Robots, Mechanism Design, Joint/Mechanism
Abstract: In-pipe robots are important for inspection of pipe network that form vital infrastructure of modern society. Nevertheless, most in-pipe robots developed so far are targeted at working inside gas pipes and not suitable for liquid pipes. This paper presents a new approach for designing in-pipe robot to work inside a liquid environment in the presence of high drag forces. Three major subsystems – propulsion, braking, and turning – are described in detail with new concepts and mechanisms that differ from conventional in-pipe robots. Prototypes of each subsystem are designed, built and tested for validation. Resulting is a robot design that navigates efficiently inside liquid pipe network and can be used for practical inspection purposes.

Attachments: Video Attachment
Keywords: Field Robots, Mechanism Design, Wheeled Robots
Abstract: This paper presents a mechanism for an in-pipe robot, called MRINSPECT VI (Multifunctional Robotic crawler for In-pipe inspection VI), which is under development for the inspection of gas pipelines with 150mm inside diameter. The mechanism is composed of multi-axial differential gear mechanism, wall pressing one, and driven by single motor. It is designed to adapt to the varying inside geometries of pipelines such as elbows by modulating the velocities of active wheels mechanically without any control effort. In this paper, the design features of the mechanism are detailed and its effectiveness is experimentally validated.

Keywords: Industrial Robots, Field Robots, Rehabilitation Robotics
Abstract: After 50 years the connections between fresh water pipes (800-1200mm diameter) need to be repaired due to aging and dissolution of the filling material. Only in Vienna 3000km of pipes need to be improved, which requires a robotic solution. The main challenge is to accurately align the robot axis with the pipe axis to enable the rotary motion of the maintenance tool. The tool system for cleaning and sealing is mounted on the maintenance unit of the robot consisting of six wheeled- legs. These legs extend to the irregular cast-iron pipe and set the robot structure eccentric to the pipe′s center. In order to center the maintenance unit, distance sensors on the legs allow to adapt to the noncircular shape of the pipe. Correcting the leg extension allows to obtain better positioning of the cleaning tool.

Attachments: Video Attachment
Keywords: Field Robots, Mechanism Design, Robotics in Hazardous Fields
Abstract: This paper describes design and development of omnidirectional magnetic climbing robots with high maneuverability for inspection of ferromagnetic 3D human made structures. The main objectives of this research is to implement a robot which is able to climb and navigate over ferromagnetic structures considering:  High maneuverability.  High speed.  Adaptability to a reasonable range of curvature.  Adaptability to a reasonable range of structures’ material and thickness.  Simplicity.

Omni-Climbers involve the following main novelties: Utilizing omni-directional wheels in order to increase maneuverability Flexible chassis with side magnets for non-actuated adaptation to the curvature

The main focus of this article is design, analyzes and implementation of magnetic omnidirectional wheels for climbing robots. We discuss the effect of the associated problems of such wheels, e.g. vibration, on climbing robots. This paper also describes the evolution of magnetic omnidirectional wheels throughout the design and development of several solutions, resulting in lighter and smaller wheels which have less vibration and adapt better to smaller radius structures. These wheels are installed on a chassis which adapts passively to flat and curved structures, enabling the robot to climb and navigate on such structures.

Attachments: Video Attachment
Keywords: Industrial Robots, Factory Automation, Domestic Robots and Home Automation
Abstract: In recent years, there has been an increasing demand to digitize a huge number of books. A promising new approach for meeting this demand, called Book Flipping Scanning, has been proposed. This is a new style of scanning in which all pages of a book are captured while a user continuously flips through the pages without stopping at each page. Although this new technology has had a tremendous impact in the field of book digitization, page turning is still done manually, which acts as a bottleneck in the development of high-speed book digitization. Against this background, this paper proposes a newly designed high-speed, high-precision book page turner machine. Our machine turns the pages in a contactless manner by utilizing the elastic force of the paper and an air blast. This design enables high-speed performance that is ten times faster than conventional approaches and, in addition, causes no obstruction in the digitization process. This paper reports the evaluation of the proposed machine using various types of paper with different qualities. Our machine achieved almost 100% success rate when turning pages at around 300 pages/min, showing that it is a promising technology for turning pages at high-speed and with high precision.

Keywords: Robot Safety, Joint/Mechanism, Collision Detection and Avoidance
Abstract: Abstract— This paper presents a robot manipulator with collision force suppression mechanism that can passively suppress collision force. The collision suppression mechanism consists of a release air pad, a transmission rack, a clutch gear and a compression spring. An air cushion bag is attached to the exterior of the robot manipulator. If a robot manipulator collides with an object or human when a task is performed, the collision force suppression mechanism disjoints the specific joint corresponding to the direction of the collision force to reduce the collision force. The robot manipulator will then return to the former task when the colliding object is eliminated. Through collision experiments, the effectiveness of the collision force suppression mechanism is verified.

Attachments: Video Attachment
Keywords: Manipulation and Compliant Assembly, Industrial Robots, Compliant Assembly
Abstract: This paper presents a visual compliance strategy to deal with the problem of fast peg-and-hole alignment with large position and attitude uncertainty. With the use of visual compliance and adoption of a light-weight 3-DOF active peg, decoupled alignment for position and attitude is realized. The active peg is capable of high-speed motion and with less dynamic defects than a traditional robot arm. Two high-speed cameras, one configured as eye-in-hand and the other as eye-to-hand are adopted to provide with the task-space feedback. Visual constraints for effecting the visual compliant motion are analyzed. Alignment experiments show that peg-and-hole alignment with the proposed approach could be successfully realized with robust convergence, and on average, the alignment could be realized within 0.7 s in our experimental setting.

Keywords: Manipulation and Compliant Assembly, Computer Vision, Compliance and Impedance Control
Abstract: In this paper, we propose a vision based compliant motion control method for part assembly work. Some industrial parts are deformed during assembly of parts. If work progress continues, deformation of the part increases, humans check the deformation and adjust force corresponding to the progress state. The proposed method enables a robot manipulator to adjust force applied for assembly work like a human. In our proposed method, force applied for the work is generated by visual information from a camera reading the deformation of the parts. Processing the visual information quantifies the deformation and the data show the work progress. NCC is generally used for template matching, but in this paper we use it for quantifying deformation. Connectors are assembled by a robot manipulator using proposed method and impedance control in experiments. Experimental results are presented to verify the effectiveness of the proposed method.

Attachments: Video Attachment
Keywords: Cooperative Manipulators, Human Centered Planning and Control, Manipulation Planning and Control
Abstract: In this paper we present a framework that allows a human and a robot to perform simultaneous manipulation tasks safely in close proximity. The proposed framework is based on early prediction of the human's motion. The prediction system, which builds on previous work in the area of gesture recognition, generates a human workspace occupancy prediction by computing the swept volume of learned human motion trajectories. The motion planner then plans robot trajectories that minimize a penetration cost in the human workspace occupancy and interleaves planning and execution. Multiple plans are computed in parallel, one for each robot task available at the current time, and the trajectory with the least cost is selected for execution. We test our framework in simulation using recorded human motion and a simulated PR2 robot. Our results show that our framework enables the robot to avoid the human while still accomplishing the robot's task, even in cases where the initial prediction of the human's motion is incorrect. We also show that taking into account human workspace occupancy prediction in the robot's motion planner leads to safer and more efficient interactions between the user and the robot than only considering the human's current configuration.

Keywords: Cooperative Manipulators, Adaptive Control
Abstract: Multi-robot cooperative manipulation of a common object requires precise kinematic coordination of the attached end effectors in order to avoid excessive forces on the object and the manipulators. A manipulation task is considered successful if the desired object motion and forces are tracked accurately. In this paper we present a systematic analysis on the effect of uncertain kinematic parameters on the tracking behavior in a planar manipulation task. An adaptive control scheme is proposed, which achieves the desired control goal asymptotically. The presented scheme employs the current force/motion data of the attached end effectors without relying on a common reference frame. The algorithm is applicable to common manipulator types with wrist-mounted force/torque sensors and implementable in real-time. The performance of the proposed control scheme is evaluated experimentally with two 7DoF manipulators who cooperatively manipulate an object of uncertain length.

Keywords: Cooperative Manipulators, Mobile Manipulation, Compliance and Impedance Control
Abstract: Cooperative manipulation in robotic teams likely results in an increased manipulation performance due to complementary sensing and actuation capabilities or increased redundancy. However, a precise coordination of the involved manipulators is required in order to avoid undesired stress on the manipulated object. Extending the workspace of the robots by means of mobile platforms greatly enlarges the potential task spectrum but simultaneously poses new challenges for example in terms of increased kinematic errors. In this paper we show how kinematic errors in the closed kinematic chain originating from uncertainties in the geometry of object and manipulators limit the cooperative task performance. We extend an impedance-based coordination control scheme towards mobile multi-robot manipulation to limit undesired internal forces in the presence of kinematic uncertainties. Furthermore, we employ a task-space decoupling approach to reduce the impact of disturbances at the mobile platforms on the end effectors. The presented control scheme for cooperative, mobile dual-arm manipulation is applicable in real-time and suitable for a team of heterogeneous manipulators. We evaluate the presented architecture by means of a large-scale experiment with four 7DoF manipulators on two mobile platforms.

Keywords: Grasping, Brain Machine Interface, Human-Robot Interaction
Abstract: Operator-machine shared control systems that automatically modulate or augment human control of robots using the concept of "Virtual Fixtures" have to our knowledge been limited to translational constraints toward simple geometric primitives. In this work we present a novel form of Virtual Fixture-based shared control that extends the concept to high dimensional control spaces and direct constraint towards irregular fixture shapes and point clouds. This "Positive-Span Virtual Fixturing" method was developed as a training mechanism to allow subjects to control 6 and 7 degree of freedom manipulators in a brain-machine interface robotic grasping experiment. Here we describe the Positive-Span Virtual Fixturing algorithm, the results from an online experiment that showed how it improved human performance in a 6-DoF robot control task, and a simulated model of how the fixturing system could potentially be integrated with automated grasp planning software to constrain manipulator action towards more dextrous tasks.

Attachments: Video Attachment
Keywords: Neurorobotics, Biomimetics, Biologically-Inspired Robots
Abstract: This study proposes a model that combines a realistically scaled neural network made up of pools of spiking neurons, with a musculoskeletal model of the human arm. We use evidence from literature to design topological pools of motor, sensory and interneurons and the nature of synaptic connections between them. The spiking output of the motor neuron pools are used as the command signals that generate motor unit forces, and drive joint motion. Feedback information from modeled muscle spindles is relayed to the neural network via monosynaptic and disynaptic pathways. We conduct experiments in specifically designed steady-state and dynamic conditions, to record participant data. Participant-specific parameters of the combined neuromusculoskeletal (NMS) system are then found using parameter identification methods. The identified NMS model is used to simulate the arm stretch reflex and the results are validated by comparison to an independent recorded dataset. The models and methodology proposed in this study show that seemingly large and complex neural systems can be identified in conjunction with the musculoskeletal systems that they control. This additional layer of detail in NMS models has important relevance to the research communities related to rehabilitation robotics and human movement analysis.

Keywords: Biologically-Inspired Robots, Biomimetics
Abstract: In this paper, we propose an "anti-fatigue" control method for bionic actuated systems. Specifically, the proposed method is illustrated on an over-actuated bionic arm. Our control method consists of two steps. In the first step, a set of linear equations is derived by connecting the acceleration description in both joint and muscle space. The pseudo inverse solution to these equations provides an initial optimal muscle force distribution. As a second step, we derive a gradient direction for muscle force redistribution. This allows the muscles to satisfy force constraints and generate an even distribution of forces throughout all the muscles (i.e. towards "anti-fatigue"). The overall proposed method is tested for a bending-stretching movement. We used two models (bionic arm with 6 and 10 muscles) to verify the method. The force distribution analysis verifies the "anti-fatigue" property of the computed muscle force. The efficiency comparison shows that the computational time does not increase significantly with the increase of muscle number. The tracking error statistics of the two models show the validity of the method.

Keywords: Biologically-Inspired Robots, Biomimetics, Cellular and Modular Robots
Abstract: Sarcomere is a functional unit constituting a skeletal muscle, which can only contract and relax in response to changes in Ca+ concentration. In order from the simple to the most complex, it builds structures corresponding to myofibrils, muscle fibers, muscle fiber bundles and the skeletal muscle. This distinctive hierarchical structure of skeletal muscles has been intensively studied in interdisciplinary research fields. In engineering, how the system efficiently controls a large number of sarcomeres to express continuous output force, is a point that has been focused. In this research, we propose a new decentralized control which is very simple but can manage many binary functional units by exploiting environmental noise. The validity of method is confirmed in both numerical simulation and a developed biologically inspired actuator.

Keywords: Biologically-Inspired Robots, Human-Robot Interaction, Humanoid Robots
Abstract: We introduce a novel humanoid robotic platform designed to jointly address three central goals to humanoid robotics: 1) study the role of morphology in biped locomotion; 2) study full-body compliant physical human-robot interaction; 3) be robust while easy and fast to duplicate to facilitate experimentation. The taken approach relies on functional modeling of certain aspects of human morphology, optimizing materials and geometry, as well as on the use of 3D printing techniques. In this article, we focus on the presentation of the design of specific morphological parts related to biped locomotion: the hip, the thigh, the limb mesh and the knee. We present initial experiments showing properties of the robot when walking with the physical guidance of a human.

Keywords: Neurorobotics, Brain Machine Interface, Adaptive Control
Abstract: To realize an autonomous odor source localization robot, we focused on the adaptability of an insect’s brain to compensate for rotational disturbances during odor source searching behavior. We manipulated motor outputs to control the sensory feedback of an insect using a brain-machine hybrid system. This system is composed of an insect’s head and a two-wheeled mobile robot. The velocity of the robot is proportional to neural activities descending from an insect brain. We successfully manipulated the behavior of the robot. In disturbance experiments, insects responded to given rotational disturbances by modifying their neural activities to make compensative angular velocity. We assumed this control system of the compensation as an output-error model. We calculated the parameters under different motor gains to reveal it as an adaptive controller. We propose that an insect has its appropriate angular velocity during odor source localization, and performed simulation experiments involving an odor source searching agent and odor distribution environment. We calculated the cost for odor source localization by changing the angular velocity of the agent, and found that it had the minimum value.

Attachments: Video Attachment
Keywords: Neurorobotics, Learning and Adaptive Systems, Adaptive Control
Abstract: It is suggested that the cerebellum can replace reflexes by anticipatory actions. Classical conditioning paradigms such as eyeblink conditioning offer a means to study the acquisition of anticipatory actions. In eyeblink conditioning a Conditioned Response (CR) to a Conditioning Stimulus (CS) is acquired such that it peaks at the expected time of arrival of a noxious Unconditioned Stimulus (US). Interestingly, the CS intensity effect links the intensity of the CS with the latency and amplitude of the CR. Having trained an animal with a tone of a certain loudness as a CS, the response to a CS of increased loudness is elicited earlier and has greater amplitude, with the opposite effect achieved lowering CS loudness. Here we propose that the CS intensity effect can be considered a built-in sensorimotor contingency applicable in the acquisition of anticipatory avoidance responses and that this contingency stems from the non-linear dynamics of the input stage of the cerebellum, conforming a generalization extrinsic to the cerebellar learning algorithm. Finally, with a robotic task, we demonstrate how this contingency between stimulus intensity and timing of the response eases the acquisition of skilled behavior as a fast action.

Keywords: Localization, Navigation, Field Robots
Abstract: This paper describes outdoor localization for a mobile robot using precise point positioning (PPP) based on the Quasi-Zenith Satellite System (QZSS) L-band Experiment (LEX) signal. For autonomous navigation applications, a real-time kinematic (RTK) global positioning system (GPS) technique is widely used to estimate user position with high-precision accuracy in real time. However, RTK-GPS requires a reference station, and there are data acquisition costs involved in estimating the position. Our approach corrects position error by applying PPP using the QZSS LEX message. PPP can estimate a single receiver position without any reference station or baseline, through use of satellite position fixing and clocks. We developed a method for extracting the QZSS LEX message in real time using a software GNSS receiver. We then constructed the PPP framework based on an LEX message containing the satellite ephemeris and clock errors. Finally, we conducted field experiments to evaluate the accuracy and precision of our proposed method. The experimental results confirmed that our method made a localization precision of 1.29 m (root mean square) possible without using a GNSS reference station.

Attachments: Video Attachment
Keywords: Localization
Abstract: In this paper, the problem of localising a robot within a known two-dimensional environment is formulated as one of minimising the Chamfer Distance between the corresponding occupancy grid map and information gathered from a sensor such as a laser range finder. It is shown that this non-linear optimisation problem can be solved efficiently and that the resulting localisation algorithm has a number of attractive characteristics when compared with the conventional particle filter based solution for robot localisation in occupancy grids. The proposed algorithm is able to perform well even when robot odometry is unavailable, insensitive to noise models and does not critically depend on any tuning parameters. Experimental results based on a number of public domain datasets as well as data collected by the authors are used to demonstrate the effectiveness of the proposed algorithm.

Keywords: Localization, Navigation
Abstract: Industrial applications often impose hard requirements on the precision of autonomous vehicle systems. As a consequence industrial Automatically Guided Vehicle (AGV) systems still use high-cost infrastructure based positioning solutions. In this paper we propose a map based localization method that fulfills the requirements on precision and repeatability, typical for industrial application scenarios. The proposed method - Normal Distributions Transform Monte Carlo Localization (NDT-MCL) is based on a well established probabilistic framework. In a novel contribution, we formulate the MCL localization approach using the Normal Distributions Transform (NDT) as an underlying representation for both map and sensor data. By relaxing the hard discretization assumption imposed by grid-map models and utilizing the piece-wise continuous NDT representation the proposed algorithm achieves substantially improved accuracy and repeatability. The proposed NDT-MCL algorithm is evaluated using offline data sets from both a laboratory and a real-world industrial environments. Additionally, we report a comparison of the proposed algorithm to grid-based MCL and to a commercial localization system when used in a closed-loop with the control system of an AGV platform. In all tests the proposed algorithm is demonstrated to provide performance superior to that of standard grid-based MCL and comparable to the performance of a commercial infrastructure based positioning system.

Keywords: Sensor Networks, Localization
Abstract: This paper proposes a scheme that exploits synergies between RSSI and camera measurements in object localization and tracking using Wireless Camera Networks (WCN). It is based on three main mechanisms: a training method that accurately adapts RSSI-range models to the particular environment; a sensor activation/deactivation method that balances the different information contribution and energy consumptions of camera and RSSI measurements; and a distributed Information Filter to integrate the available measurements. The joint use of these mechanisms drastically reduces energy consumption -40%- with no significant degradation w.r.t. existing schemes based on only cameras and shows better robustness to target occlusions. The scheme has been implemented and validated in the indoor CONET Integrated Testbed.

Keywords: Range Sensing, Localization, Mapping
Abstract: Abstract--- This paper is about estimating a smooth, continuous-time trajectory of a vehicle relative to a prior 3D laser map. We pose the estimation problem as that of finding a sequence of Catmull-Rom splines which optimise the Kernelised Rényi Distance (KRD) between the prior map and live measurements from a 3D laser sensor. Our approach treats the laser measurements as a continual stream of data from a smoothly moving vehicle. We side-step entirely the segmentation and feature matching problems incumbent in traditional point cloud matching algorithms, relying instead on a smooth and well behaved objective function. Importantly our approach admits the exploitation of sensors with modest sampling rates - sensors that take seconds to densely sample the workspace. We show how by appropriate use of the Improved Fast Gauss Transform we can reduce the order of the estimation problem from quadratic (straight forward application of the KRD) to linear. Although in this paper we use 3D laser, our approach is also applicable to vehicles using 2D laser sensing or dense stereo. We demonstrate and evaluate the performance of our approach when estimating the full 6DOF continuous time pose of a road vehicle undertaking over 2.7km of outdoor travel.

Keywords: Localization, Mapping, Sensor Fusion
Abstract: Abstract— Estimating the pose in real-time is a primary func-tion for intelligent vehicle navigation. Whilst different solutions exist, most of them rely on the use of high-end sensors. This paper proposes a solution that exploits an automotive type L1-GPS receiver, features extracted by low-cost perception sensors and vehicle proprioceptive information. A key idea is to use the lane detection function of a video camera to retrieve accurate lateral and orientation information with respect to road lane markings. To this end, lane markings are mobile-mapped by the vehicle itself during a first stage by using an accurate localizer. Then, the resulting map allows for the exploitation of camera-detected features for autonomous real-time localization. The results are then combined with GPS estimates and dead-reckoning sensors in order to provide localization information with high availability. As L1-GPS errors can be large and are time correlated, we study in the paper several GPS error models that are experimentally tested with shaping filters. The approach demonstrates that the use of low-cost sensors with adequate data-fusion algorithms should lead to computer-controlled guidance functions in complex road networks.

Keywords: Mechanism Design, Parallel Robots, Micro-manipulation
Abstract: In this paper, the design of a high precision device using a Linear Delta manipulator was proposed to compensate for the tremor signal in three translational directions. A Linear Delta manipulator is a suitable tremor suppression device due to the simple structure and high stiffness with the vertical direction in the application of micro manipulation such as microsurgery and cell manipulation. In order to implement the mechanism of the Linear Delta manipulator to the device, three voice coil motors and three linear encoders with high resolution were used. The flexure mechanism was applied to the device to avoid the friction effect of the small ball joint. Finally, the experiments for the validation of the proposed device were performed as follows: (1) position control in each axis for accuracy, and (2) sine wave tracking (500 micrometers, 12Hz) for bandwidth of the system.

Keywords: Range Sensing, Industrial Robots, Factory Automation
Abstract: This study proposed the ultra-wideband(UWB) sensor to detect the vibration of the delta robot and the distance between UWB sensor and robot arm. Based on the radar propagating principle and the proposed algorithm, the vibration status of robot arm can be obtained. Besides, the vibration status can be reduced by feedback the information to the controller of the robot arm. The advantage of the proposed sensor is that without contacting to the robot arm, UWB sensor is more flexible to be used and will not cause any unnecessary payload as accelerometers. With proper calibration, the simulation of vibration frequency and the real-time absolute position of the robot arm were calculated and demonstrated. The experimental results show that the correlations for measured frequency and distance approximate to 1.

Keywords: Parallel Robots, Visual Tracking
Abstract: To control dynamics of a parallel robot, we should measure the state feedback accurately and fast. In this paper, we show how to estimate positions and velocities simultaneously (i.e., the state feedback) at a reasonable accuracy and speed. We did this using only the sequential visual contours of the legs. A single-iteration virtual visual servoing scheme regulates rapidly an error of these contours. We validated this theory, a step to control parallel robots at high speed by their leg kinematics, with simulations and experiments.

Keywords: Parallel Robots, Visual Servoing, Kinematics
Abstract: Previous works on the Gough-Stewart (GS) platform have shown that its visual servoing using the observation of its leg directions was possible by observing only three of its six legs but that the convergence to the desired pose was not guarantied. This can be explained by considering that the visual servoing of the leg direction of the GS platform was equivalent to controlling another robot, the 3-UPS that has assembly modes and singular configurations different from those of the GS platform. Considering this hidden robot model allowed the simplification of the singularity analysis of the mapping between the leg direction space and the Cartesian space. In this paper, the work on the definition of the hidden robot models involved in the visual servoing using the observation of the robot leg directions is extended to another robot, the Adept Quattro. It will be shown that the hidden robot model is completely different from the model involved in the control of the GS platform. Therefore, the results obtained for the GS platform are not valuable for this robot. The hidden robot has assembly modes and singular configurations different from those of the Quattro. An accuracy analysis is performed to show the importance of the leg selection. All these results are validated on a Quattro simulator created using ADAMS/Controls and interfaced with Matlab/Simulink.

Keywords: Parallel Robots, Joint/Mechanism, Redundant Robots
Abstract: This paper presents a novel 4 dofs (3T-1R) parallel redundant mechanism, with its complete study regarding inverse and direct geometric models (IGM and DGM), as well as singularity and workspace analysis. The robot is capable of performing a half-turn about the z axis (a complete turn would be theoretically possible if it were not for possible unavoidable inter-collisions in the practical case), and having all of its prismatic actuators along one direction, enables it to have an independent x motion - only limited by the stroke of the prismatic actuators. The mechanism is characterized by elevated dynamical capabilities having its actuators at base. Moreover, the performance of the robot is evaluated considering isotropy in velocity and forces.

Keywords: Parallel Robots, Kinematics, Mechanism Design
Abstract: This paper presents a parallel and partially decoupled mechanism characterized by three translational and two rotational degrees of freedom. A set of parallel kinematic chains actuates five degrees of freedom of the mobile platform and constrains one of its rotations. Its kinematics combines advantages typical of parallel architectures, as high dynamics, with positive aspects of partially decoupled ones, in terms of mechanical design, control and motion planning, through a relatively simple direct kinematic formulation. The presented architecture constitutes the mechanical heart of a robotic prototype designed to actively support the patient's head in open-skull awake surgery.

Keywords: Teleoperated surgical systems, Haptics and Haptic Interfaces, Kinematics
Abstract: One of the main limitations of systems for Minimally Invasive Robotic Surgery is the lack of haptic feedback. In this paper, a teleoperated system for robotic surgery is introduced, able to guide the surgeon towards a target anatomy by providing her with force feedback based on Virtual Fixtures (VF). The teleoperated system has a redundant slave robot. A closed-form inverse kinematics is proposed to solve redundancy that is based on an optimization approach in one variable. Four different cost objective functions are proposed in the paper and one is implemented and validated, i.e. the cost function aimed at minimizing the amount of space of the robot in the operative theater during the surgical procedure. The proposed teleoperated architecture has been tested on a teleoperated system composed of a 3-DoFs haptic joystick and a 7-DoFs anthropomorphic manipulator. Experimental tests on 12 volunteer subjects have been carried out. Results demonstrate that a force feedback based on VF provides a statistically significant enhancement of procedure accuracy.

Keywords: Teleoperated surgical systems, Telerobotics, Surgical Robotics
Abstract: Tele-surgery has been more and more popular in robot-assisted medical intervention. Most existing teleoperation architectures for medical applications adopt 2-channel architectures. The 2-channel architectures have been evaluated in literature and it is shown that some architectures, e.g. positionforce (P-F), are able to provide the surgeon a reliable haptic sense of the working environment (transparency). However, stability of these P-F architecture is still a considerable concern especially when physiological disturbances exist in the remote environment. P-PF architecture is proved to provide a convenient alternative. With one more channel 3-channel teleoperation architectures present promising options due to their augmented design flexibility. This paper evaluates stability and transparency of general 3-channel bilateral teleoperation control architectures and provides a design framework guidelines to improve the architectures’ stability robustness and optimize the transparency. Simulation evaluations are provided to illustrate how the optimal 3-channel teleoperation architecture is chosen for medical applications given their dedicated requirements.

Keywords: Force and Tactile Sensing, Medical Robots and Systems, Haptics and Haptic Interfaces
Abstract: This work is aimed at developing a new minimally invasive approach to characterize tissue properties in real time during telerobotic palpation and to localize tissue abnormality while estimating its depth. This method relies on using a minimally invasive probe with a rigidly mounted tactile sensor at the tip to capture the force distribution map and the indentation depth by each tactile element and thereby generating a stiffness map for the palpated tissue. The hybrid impedance control technique is used for this approach to enable the operator to switch between position control and force control and thereby to autonomously obtain the required information from the remote tissue. The operator would then be able to localize tissue abnormality based on the force distribution map, the tissue stiffness map and the indentation depth which are visually presented to him/her in real time. This method also enables the operator to estimate the depth at which the tissue abnormality is located. Our results show that tactile sensing alone may be unable to detect tumors embedded deep inside tissue and may also not be a good alternative for palpation on uneven tissue surfaces.

Attachments: Video Attachment
Keywords: Teleoperated surgical systems, Visual Tracking, Medical Robots and Systems
Abstract: This study presents one of the enabling technologies for teleoperated bevel-tip needle steering under real-time MRI guidance i.e. capability of tracking the needle with higher accuracy and bandwidth than real-time MRI. Three fibers, each with three Fiber Bragg Gratings (FBG) were embedded into a 0.6 mm inner stylet of a 20G MRI-compatible biopsy needle. The axial force caused by the bevel-tip was considered in the analysis using beam-column theory. Since the insertion depth is varying, the minimum number of sensors and their optimal locations in the fibers were determined such that the tip position error estimation is below 0.5 mm for all insertion depths. A practical and accurate calibration method for the apparatus is presented. The instrumented needle was fabricated to fit in the needle driver unit of a MRI-compatible needle steering robot. The tracking apparatus was calibrated, including compensation for temperature changes in tissue during insertion. Experimental results showed needle tip tracking error below 0.5 mm at different insertion depths. Real-time 3D shape of the needle was visualized in 3D Slicer yielding navigation of the needle in real-time.

Keywords: Telerobotics, Rehabilitation Robotics
Abstract: The problem of designing of a haptics-enabled teleoperated rehabilitation system in the presence of communication delays is addressed. In a teleoperated rehabilitation system communication delays introduce phase shift which may result in the task inversion phenomenon. To overcome task inversion, a new type of projection-based force reflection algorithm is proposed which is suitable for assistive/resistive therapy in the presence of irregular communication delays. Additionally, algorithms for augmented therapy are introduced which combine the projection-based force reflection with a delay-free local virtual therapist. A small-gain design is developed which guarantees stability of the proposed schemes for both assistive and resistive modes of the therapy. Simulations and experimental results are presented which confirm the improvement achieved by the proposed methods.

Keywords: Teleoperated surgical systems, Surgical Robotics, Tendon/Wire Mechanism
Abstract: STRAS is a flexible robotic system based on the Anubis platform from Karl Storz and is aimed for intraluminal and transluminal procedures. It is composed of three cable-driven sub-systems, one endoscope and two insertable instruments. The bending instruments have three degrees of freedom and can be teleoperated by the user via two commercial master interfaces (Omega.7, Force Dimension). In this paper we investigate several ways to map the motions from the master side to the instruments, from joint per joint control to cartesian control. We describe these mappings and compare them in elementary tasks in an attempt to analyze how non-linearities affect the accuracy of control. Results show that joint control and pseudo-cartesian control provide equivalent accuracy but with different difficulties for the user.

Keywords: Micro-manipulation, Nano manipilation, Nano automation
Abstract: This paper presents the use of robotically controlled optical tweezers to manipulate a group of cells into a region of interest to form the required pattern. A novel multilevel-based topology is designed to present different cell patterns in the region of interest. A potential function-based controller is developed to control the cells to form the required pattern. A pattern regulatory control force is developed which particularly addresses the special case when cells stop at undesired positions. The system stability is analyzed using Lyapunov approach. Experiment is performed with robotically controller optical tweezers to demonstrate the effectiveness of the proposed approach.

Keywords: Micro-manipulation, Automation in Life Sciences: Biotechnology, Pharmaceutical and Health Care, Visual Tracking
Abstract: Microinjection and biopsy of oocytes and embryos in Assisted Reproductive Technology (ART) require highly delicate handling of cells. In particular, efficient control of cell orientation is necessary to maintain their integrity during tool penetration, which currently remains challenging to accomplish by the existing method of repeated aspiration/release via micropipette. We present a microfluidic platform to automate the process of cell orientation control and trapping by means of hydrodyanmic force and vision-based position control. The device is accessible by conventional micropipettes via a cavity, allowing immobilized cells to be operated on. An orientation control algorithm based on the movement of the embryo within the microchannel is proposed. Visual tracking of the polar body is used to provide the information of cell orientation. Experimental results with mouse embryos indicate that cell orientation can be systematically controlled autonomously without human intervention and therefore provides a framework for further development of robotics approach to precise manipulation of microparticles within microfluidic devices.

Keywords: Automation in Life Sciences: Biotechnology, Pharmaceutical and Health Care, Micro-manipulation, Visual Tracking
Abstract: Piezoelectric inkjet printer technology recently has gained attention and was utilized eject particles and cells of several tens of μm scale, which is large compared to colloid used in printer ink. However, the inkjet head was originally design for color ink. Therefore, problems, such as, head clogging and trajectory error occurred. In this study, those problems were addressed, and optimal condition for stable cells ejection was verified. Furthermore, one cell per one droplet printing method was established by observing cells position on the inside of inkjet head. Finally, automatic one cell per one droplet printing system was successfully developed by processing image of the inkjet head to automatically detect cells position. The automatic one cell per one droplet printing system was successfully developed with 98% successful ratio.

Keywords: Micro-manipulation, Micro/Nano Robots, Motion Control
Abstract: This paper proposed a Multiple Microfluidic Stream based Manipulation (MMSM) system for bio-objects using micro hydrodynamics and Lab on Chip (LOC) technology. Our method can implement the function of micro manipulation and micro assembly of bio-objects without contact in an open space. Compared with other conventional bio-micro manipulation and assembly methods, this system is manipulating a micro object by controlling multiple microfluidic streams onto it from various directions. The advantage of this method is open space, multi-function, multi-scale, multi degree of freedom, and non-invasive three dimensions manipulation. These microfluidic streams are generated simultaneously from multiple orifices. By regulating the parameters of the microfluidic stream such as flow rates, position and number of operating orifices, the direction and velocity of the object can be controlled. To verify this principle, we designed an open space fluidic system for on-chip manipulation, and calculated velocity and direction of the microfluidic stream using CFD simulation. Then the prototype microchip with an array of 9 orifices was fabricated with glass. In experiments, demonstrations of rectilinear motion of a single cell and micro particle were observed. The results presented in this paper showed that this MMSM has the capability for bio micro manipulation and micro assembly of bio-object.

Keywords: Micro-manipulation
Abstract: Recently the research about constructing 3 dimensional cell structures is very important for its great potential applications in tissue engineering. In this paper, we report a novel method of constructing multi-layered microstructures embedding cells via microfluidic devices. The on-chip fabrication of movable microstructures embedding fibroblasts (NIH/3T3) based on Poly (ethylene glycol) Diacrylate (PEGDA) was reported. Two approaches for assembling these movable microstructures were presented. One was a manual assembly method based on micromanipulation system and the other one was a self-assembly method based on microfluidic channel. Several manual assembly ways were demonstrated and a tube-shaped microstructure with 17 layers was assembled by an efficient assembly method. A novel microfluidic channel was presented for conducting self-assembly method and a 2-layered experimental microfluidic device was fabricated by Polydimethylsiloxane (PDMS). The self-assembly process of fabricated microstructures via this device was preliminarily demonstrated.

Attachments: Video Attachment
Keywords: Micro/Nano Robots, Nano assembly, Nano automation
Abstract: Roboticists, biologists, and chemists are now producing large populations of simple robots, but controlling large populations of robots with limited capabilities is difficult, due to communication and onboard-computation constraints. Direct human control of large populations seems even more challenging. In this paper we investigate control of mobile robots that move in a 2D workspace using three different system models. We focus on a model that uses broadcast control inputs specified in the global reference frame. In an obstacle-free workspace this system model is uncontrollable because it has only two controllable degrees of freedom---all robots receive the same inputs and move uniformly. We prove that adding a single obstacle can make the system controllable, for any number of robots. We provide a position control algorithm, and demonstrate through extensive testing with human subjects that many manipulation tasks can be reliably completed, even by novice users, under this system model, with performance benefits compared to the alternate models.

We compare the sensing, computation, communication, time, and bandwidth costs for all three system models. Results are validated with extensive simulations and hardware experiments using over 100 robots.

Keywords: SLAM, Localization, Calibration and Identification
Abstract: Large position errors plague GNSS-based sensors (e.g., GPS) due to poor satellite configuration and multipath effects, resulting in frequent outliers. Due to quadratic cost functions when optimizing SLAM via nonlinear least square methods, a single such outlier can cause severe map distortions. Following in the footsteps of recent improvements in the robustness of SLAM optimization process, this work presents a framework for improving sensor noise characterizations by combining a machine learning approach with max-mixture error models. By using max-mixtures, the sensor's noise distribution can be modeled to a desired accuracy, with robustness to outliers. We apply the framework to the task of accurately modeling the uncertainties of consumer-grade GPS sensors. Our method estimates the observation covariances using only weighted feature vectors and a single max operator, learning parameters off-line for efficient on-line calculation.

Keywords: SLAM, Localization
Abstract: A major challenge for robot localization and mapping systems is maintaining reliable operation in a changing environment. Vision-based systems in particular are susceptible to changes in illumination and weather, and the same location at another time of day may appear radically different to a system using a feature-based visual localization system. One approach for mapping changing environments is to create and maintain maps that contain multiple representations of each physical location in a topological framework or manifold. However, this requires the system to be able to correctly link two or more appearance representations to the same spatial location, even though the representations may appear quite dissimilar. This paper proposes a method of linking visual representations from the same location without requiring a visual match, thereby allowing vision-based localization systems to create multiple appearance representations of physical locations. The most likely position on the robot path is determined using particle filter methods based on dead reckoning data and recent visual loop closures. In order to avoid erroneous loop closures, the odometry-based inferences are only accepted when the inferred path’s end point is confirmed as correct by the visual matching system. Algorithm performance is demonstrated using an indoor robot dataset and a large outdoor camera dataset.

Keywords: SLAM, Search and Rescue Robots, Mapping
Abstract: Learning a map of an unknown environment and localising a robot in it is a common problem in robotics, with solutions usually requiring an estimate of the robot’s motion. In scenarios such as Urban Search and Rescue, motion encoders can be highly inaccurate, and weight and battery requirements often limit computing power. We have developed a GPU based algorithm using Iterative Closest Point position tracking and Graph SLAM that can accurately generate a map of an unknown environment without the need for motion encoders and requiring minimal computational resources. The algorithm is able to correct for drift in the position tracking by rapidly identifying loops and optimising the map. We present a method for refining the existing map when revisiting areas to increase the accuracy of the existing map and bound the run-time to the size of the environment.

Keywords: SLAM, Mapping, Localization
Abstract: In this paper we present a system for capturing large scale dense maps in an online setting with a low cost RGB-D sensor. Central to this work is the use of an "as-rigid-as-possible" space deformation for efficient dense map correction in a pose graph optimisation framework. By combining pose graph optimisation with non-rigid deformation of a dense map we are able to obtain highly accurate dense maps over large scale trajectories that are both locally and globally consistent. With low latency in mind we derive an incremental method for deformation graph construction, allowing multi-million point maps to be captured over hundreds of metres in real-time. We provide benchmark results on a well established RGB-D SLAM dataset demonstrating the accuracy of the system and also provide a number of our own datasets which cover a wide range of environments, both indoors, outdoors and across multiple floors.

Keywords: SLAM
Abstract: In this paper, we model the robust loop-closure pose-graph SLAM problem as a Bayesian network and show that it can be solved with the Classification Expectation-Maximization (EM) algorithm. In particular, we express our robust pose-graph SLAM as a Bayesian network where the robot poses and constraints are latent and observed variables. An additional set of latent variables is introduced as weights for the loop-constraints. We show that the weights can be chosen as the Cauchy function, which are iteratively computed from the errors between the predicted robot poses and observed loop-closure constraints in the Expectation step, and used to weigh the cost functions from the pose-graph loop-closure constraints in the Maximization step. As a result, outlier loop-closure constraints are assigned low weights and exert less influences in the pose-graph optimization within the EM iterations. To prevent the EM algorithm from getting stuck at local minima, we perform the EM algorithm multiple times where the loop constraints with very low weights are removed after each EM process. This is repeated until there are no more changes to the weights. We show proofs of the conceptual similarity between our EM algorithm and the M-Estimator. Specifically, we show that the weight function in our EM algorithm is equivalent to the robust residual function in the M-Estimator. We verify our proposed algorithm with experimental results from multiple simulated and real-world datasets, and comparisons with other existing works.

Keywords: SLAM, Computer Vision
Abstract: In this paper, we propose a method to compute the pose-graph loop-closure constraints using multiple non/minimal overlapping field-of-views cameras mounted rigidly on a self-driving car without the need to reconstruct any 3D scene points. In particular, we show that the relative pose with metric scale between two loop-closing pose-graph vertices can be directly obtained from the epipolar geometry of the multi-cameras system. As a result, we avoid the additional time complexities and uncertainties from the reconstruction of 3D scene points which are needed by standard monocular and stereo approaches. In addition, there is a greater flexibility in choosing a configuration for the multi-camera system to cover a wider field-of-view so as to avoid missing out any loop-closure opportunities. We show that by expressing the point correspondences between two frames as Pluecker lines and enforcing the planar motion constraint on the car, we are able to use multiple cameras as one and formulate the relative pose problem for loop-closure as a minimal problem which requires 3-point correspondences that yields up to six real solutions. The RANSAC algorithm is used to determine the correct solution and for robust estimation. We verify our method with results from multiple large-scale real-world data.

Attachments: Video Attachment
Keywords: Visual Servoing, Visual Tracking
Abstract: In this paper we address the problem of visibility in position-based visual servoing. It is well known that the observed object may leave the field of view in such schemes, as there is usually no control in the image. Recent control schemes try to cope with this issue by defining an image-based constraint such that the object stays in the image. We propose to increase the convergence domain of such schemes by defining a new constraint that allows the observed object to leave partially the field of view. The general formulation is exposed and the computation of this constraint is detailed. Experiments show that controlling the visibility loss allows performing position-based visual servoing tasks that were impossible to perform while keeping the whole object in the image.

Attachments: Video Attachment
Keywords: Visual Servoing, Motion and Path Planning, Learning from Demonstration
Abstract: Vision feedback control techniques are desirable for a wide range of robotics applications due to their robustness to image noise and modeling errors. However in the case of a robot-mounted camera, they encounter difficulties when the camera traverses large displacements. This scenario necessitates continuous visual target feedback during the robot motion, while simultaneously considering the robot's self- and external- constraints. Herein, we propose to combine workspace (Cartesian space) path-planning with robot teach-by-demonstration to address the visibility constraint, joint limits and ``whole arm" collision avoidance for vision-based control of a robot manipulator. User demonstration data generates safe regions for robot motion with respect to joint limits and potential ``whole arm" collisions. Our algorithm uses these safe regions to generate new feasible trajectories under a visibility constraint that achieves the desired view of the target (e.g., a pre-grasping location) in new, undemonstrated locations. Experiments with a 7-DOF articulated arm validate the proposed method.

Keywords: Visual Servoing, Wheeled Robots
Abstract: In this paper, an uncalibrated visual servo regulation strategy is designed for a nonholonomic mobile robot equipped with an eye-in-hand camera, which drives the mobile robot to the target pose with exponential convergence. Specifically, a novel fundamental matrix-based algorithm is firstly proposed to rotate the robot to point toward the desired position, with the camera intrinsic parameters estimated simultaneously by employing the fundamental matrix and a projection homography matrix. Subsequently, by utilizing the obtained camera intrinsic parameters, a straight-line motion controller is developed to drive the robot to the desired position, with the orientation of the robot always facing the target position. Another pure rotation controller is finally adopted to correct the orientation error. The exponentially convergent properties of the visual servo errors are proven with mathematical analysis. The performance of the proposed uncalibrated visual servo regulation method is further validated by simulation results.

Attachments: Video Attachment
Keywords: Visual Servoing, Wheeled Robots, Service Robots
Abstract: In this paper, we present an autonomous navigation framework of a wheelchair by means of a single camera and visual servoing. We focus on a corridor following task where no prior knowledge of the environment is required. Our approach embeds an image-based controller, thus avoiding to estimate the pose of the wheelchair. The servoing process matches the non holonomous constraints of the wheelchair and relies on two visual features, namely the vanishing point location and the orientation of the median line formed by the straight lines related to the bottom of the walls. This overcomes the process initialization issue typically raised in the literature. The control scheme has been implemented onto a robotized wheelchair and results show that it can follow a corridor with an accuracy of +/- 3cm.

Attachments: Video Attachment
Keywords: Visual Servoing, Visual Tracking, Unmanned Aerial Vehicles
Abstract: Pose estimation is a key component for robot navigation. An Unmanned Aerial Vehicle (UAV) that is instructed to reach certain location requires a way of measuring its pose. This article presents a method for UAV visual servoing that uses the 3D pose of the drone as controller feedback. A remote monocular camera observes the tracked UAV while it moves and rotates in a 3D space. Pose is obtained from a 3D tracking process based on a cuboid model. In particular, a simultaneous face tracking strategy where 3D pose estimations from different faces are combined is introduced. Face combination was validated using a robotic arm with a cuboid at the final joint. For the UAV control, hover and path following tasks were tested. Results show that the proposed method correctly handles changes in pose, even though no face is always visible. Also, the UAV maintained a low speed in order to satisfy the small inter-frame displacement constraint imposed by visual tracking algorithm.

Keywords: Visual Servoing, SLAM, Visual Navigation
Abstract: Abstract--- This paper presents a novel vision-based localization and mapping algorithm using image moments of region features. The environment is represented using regions, such as planes and/or 3D objects instead of only a dense set of feature points. The regions can be uniquely defined using a small number of parameters; e.g., a plane can be completely characterized by normal vector and distance to a local coordinate frame attached to the plane. The variation of image moments of the regions in successive images can be related to the parameters of the regions. Instead of tracking a large number of feature points, variations of image moments of regions can be computed by tracking the segmented regions or a few feature points on the objects in successive images. A map represented by regions can be characterized using a minimal set of parameters. The problem is formulated as a nonlinear filtering problem. A new discrete-time nonlinear filter based on the state-dependent coefficient (SDC) form of nonlinear functions is presented. It is shown via Monte-Carlo simulations that the new nonlinear filter is more accurate and consistent than EKF by evaluating the root-mean squared error (RMSE) and normalized estimation error squared (NEES).

Attachments: Video Attachment
Keywords: Learning from Demonstration, Learning and Adaptive Systems
Abstract: Gestures are characterized by intermediary or final landmarks (real or virtual) in task space or joint space that can change during the course of the motion, and that are described by varying accuracy and correlation constraints. Generalizing these trajectories in robot learning by imitation is challenging, because of the small number of demonstrations provided by the user. We present an approach to statistically encode movements in a task-parameterized mixture model, and derive an expectation-maximization (EM) algorithm to train it. The model automatically extracts the relevance of candidate coordinate systems during the task, and exploits this information during reproduction to adapt the movement in real-time to changing position and orientation of landmarks or objects. The approach is tested with a robotic arm learning to roll out a pizza dough. It is compared to three categories of task-parameterized models: 1) Gaussian process regression (GPR) with a trajectory models database; 2) Multi-streams approach with models trained in several frames of reference; and 3) Parametric Gaussian mixture model (PGMM) modulating the Gaussian centers with the task parameters. We show that the extrapolation capability of the proposed approach outperforms existing methods, by extracting the local structures of the task instead of relying on interpolation principles.

Attachments: Video Attachment
Keywords: Human-Robot Interaction, Distributed Robot Systems, Aerial Robotics
Abstract: Extending our previous work in real-time vision-based human robot interaction with multi-robot systems, we present the first example of creating, modifying and commanding teams of UAVs by an uninstrumented human. To create a team the user focuses attention on an individual robot by simply looking at it, then adds or removes it from the current team with a motion-based hand gesture. Another gesture commands the entire team to begin task execution. Robots communicate among themselves by wireless network to ensure that no more than one robot is focused, and so that the whole team agrees that it has been commanded. Since robots can be added and removed from the team, the system is robust to incorrect additions. A series of trials with two and three very low-cost UAVs and off-board processing demonstrates the practicality of our approach.

Attachments: Video Attachment
Keywords: Human detection and tracking, Robot Companions and Social Human-Robot Interaction, Unmanned Aerial Vehicles
Abstract: In this paper, we present an approach that allows a quadrocopter to follow a person and to recognize simple gestures using an onboard depth camera. This enables novel applications such as hands-free filming and picture taking. The problem of tracking a person with an onboard camera however is highly challenging due to the self-motion of the platform. To overcome this problem, we stabilize the depth image by warping it to a virtual-static camera, using the estimated pose of the quadrocopter obtained from vision and inertial sensors using an Extended Kalman filter. We show that such a stabilized depth video is well suited to use with existing person trackers such as the OpenNI tracker. Using this approach, the quadrocopter not only obtains the position and orientation of the tracked person, but also the full body pose -- which can then for example be used to recognize hand gestures to control the quadrocopter's behaviour. We implemented a small set of example commands (``follow me'', ``take picture'', ``land''), and generate corresponding motion commands. We demonstrate the practical performance of our approach in an extensive set of experiments with a quadrocopter. Although our current system is limited to indoor environments and small motions due to the restrictions of the used depth sensor, it indicates that there is large potential for such applications in the near future.

Keywords: Human detection and tracking
Abstract: In this paper, we present a fast Histogram of Oriented Gradients (HOG) based person detector. The detector adopts a cascade of rejectors framework by selecting discriminant features via a new proposed feature selection framework based on Binary Integer Programming. The mathematical programming explicitly formulates an optimization problem to select discriminant features taking detection performance and computation time into account. The learning of the cascade classifier and its detection capability are validated using a proprietary dataset acquired using the Ladybug2 spherical camera and the public INRIA person detection dataset. The final detector achieves a comparable detection performance as Dalal and Triggs~cite{Dalal05} detector while achieving on average more than 2.5x - 8x speed up depending on the training dataset.

Attachments: Video Attachment
Keywords: Human detection and tracking, Visual Tracking, Collision Detection and Avoidance
Abstract: We propose and evaluate a system for detecting and tracking multiple humans wearing high-visibility clothing from vehicles operating in industrial work environments. We use a customized stereo camera setup equipped with IR flash and IR filter to detect the reflective material on the worker's garments and estimate their trajectories in 3D space. An evaluation in two distinct industrial environments with different degrees of complexity demonstrates the approach to be robust and accurate for tracking workers in arbitrary body poses, under occlusion, and under a wide range of different illumination settings.

Keywords: Aerial Robotics
Abstract: An accurate and computationally very fast multi-modal human detector is presented. This 1D+2D detector fuses 1D range scan and 2D image information via an effective geometric descriptor and a silhouette based visual representation within a radial basis function kernel support vector machine learning framework. Unlike the existing approaches, the proposed 1D+2D detector does not make any restrictive assumptions on the range scan positions, thus it is applicable to a wide range of real-life detection tasks. To analyze the discriminative power of the geometric descriptor, a range scan only version, 1D+, is also evaluated. Extensive experiments demonstrate that the 1D+2D detector works robustly under challenging imaging conditions and achieves several orders of magnitude performance improvement while reducing the computational load drastically.

In addition, a new multi-modal (LIDAR, depth image, optical image) dataset, DontHitMe, is introduced. This dataset contains 40,000 registered frames and 3,600 manually annotated human objects. It depicts challenging illumination conditions in indoors and outdoors environments and is publicly available to our community.

Attachments: Video Attachment
Keywords: Force and Tactile Sensing, Human detection and tracking, Human-Robot Interaction
Abstract: We have developed a net-structure proximity sensor that detects the azimuth and elevation to a nearby object. This information can be used by robots to avoid obstacles or to respond to human behavior. We propose detection principles where the azimuth is detected by arranging two one-dimensional net-structure proximity sensors along orthogonal axes, and the elevation is detected by arranging two one-dimensional net-structure proximity sensors in a stacked ring. We also experimentally demonstrate the feasibility of these detection principles. The experimental result shows the sensor can detect azimuth at all peripheral angles and elevation from side to top up.

Keywords: Personal Robots, Motion Control, Human detection and tracking
Abstract: Recently, a super-aging society has developed in many countries around the world. The research and development of PRs (personal robots) that improve the quality of human life is needed in order to accommodate the aging society. Elderly people will be able to spend their lives happily and effortlessly with the aid of useful and convenient PRs. However, excessive or premature use of PRs may cause health deterioration or contribute to the quick aging phenomenon. In this paper, a new prototype PR is proposed that can follow human beings with their baggage. Elderly people, therefore, will be able to go outside empty handed to shop, enjoy the fresh air, and visit friends. This PR will encourage people to walk outside and can eventually support an active lifestyle in its true sense. For actual use, PRs should have both a small footprint for coexistence in human society and high traveling performance for following the human wherever they go. Active posture control for the roll and pitch angles is applied to the PR to realize these requirements. The proposed structure and control approach using lateral acceleration as a control variable is verified by experiment using the new prototype robot.

Keywords: Virtual Reality and Interfaces, Telerobotics, Omnidirectional Vision
Abstract: This paper proposes a teleoperation interface by which an operator can control a robot from freely configured viewpoints using realistic images of the physical world. The viewpoints generated by the proposed interface provide human operators with intuitive control using a head-mounted display and head tracker, and assist them to grasp the environment surrounding the robot. A state-of-the-art free-viewpoint image generation technique is employed to generate the scene presented to the operator. In addition, an augmented reality technique is used to superimpose a 3D model of the robot onto the generated scenes. Through evaluations under virtual and physical environments, we confirmed that the proposed interface improves the accuracy of teleoperation.

Attachments: Video Attachment
Keywords: Human-Robot Interaction, Medical Systems, Healthcare, and Assisted Living, Rehabilitation Robotics
Abstract: In this study, we propose a steering control method for a cycling wheelchair. The commercially available cycling wheelchair is a pedal-driven system that is similar to a bicycle, and patients with impairment of their lower extremities can move the wheelchair based on the pedaling force if they can slightly move their legs by themselves. The user can also change the wheelchair direction using the steering handle. However, right and left turns are perceived differently and a large steering torque is required while operating the steering handle because of hardware problems associated with the cycling wheelchair. To overcome this problem, we propose a new hardware solution and a method for steering motion control using servo brakes for the cycling wheelchair. The proposed method is applied to the developed cycling wheelchair, and the experimental results illustrate the validity of the system.

Keywords: Human Centered Automation, Human-Robot Interaction, Humanitarian technology for energy, environment and safety
Abstract: A bicycle riding with toddlers becomes convenient and　indispensable transportation for parents in Japan. On the other hand, the bicycle with toddlers tends to be less-stable when start moving, low-speed biking and abrupt steering　because it is hard to steer due to increasing the moment of inertia of the handlebars. Hence this study proposes a power steering system for electrically-assisted bicycles riding with a toddler. The power steering system is designed to allow a rider to steer the handlebars with a toddler as if steer the handlebars without him. The power steering system is mounted on a real bicycle, and its effectiveness is verified through experiments.

Attachments: Video Attachment
Keywords: Visual Learning, Learning and Adaptive Systems, Learning from Demonstration
Abstract: We present a novel robot learning approach based on visual perception that allows a robot to acquire new skills by observing a demonstration from a tutor. Unlike most existing learning from demonstration approaches, where the focus is placed on the trajectories, in our approach the focus is on achieving a desired goal configuration of objects relative to one another. Our approach is based on visual perception which captures the object's context for each demonstrated action. This context is the basis of the visuospatial representation and encodes implicitly the relative positioning of the object with respect to multiple other objects simultaneously. The proposed approach is capable of learning and generalizing multi-operation skills from a single demonstration, while requiring minimum a priori knowledge about the environment. The learned skills comprise a sequence of operations that aim to achieve the desired goal configuration using the given objects. We illustrate the capabilities of our approach using three object reconfiguration tasks with a Barrett WAM robot.

Keywords: Learning and Adaptive Systems, Autonomous Agents
Abstract: In this paper, novel reinforcement learning method with intrinsic motivation for reproducibility of the past successful experience is presented. The experience is extracted as skill, which is composed of action sequence and abstract knowledge about observed sensor input. Utilizing the collected skills, reproduction of the successful experience is attempted in novel and unknown environment. Consistent exploration and active reduction of search space are realized by learning with intrinsic motivation for reproducibility of experience. Simulation experiments in grid world demonstrate that proposed method significantly accelerate speed of learning.

Keywords: Learning and Adaptive Systems, Human Performance Augmentation, Human-Robot Interaction
Abstract: Abstract— Human intention estimation is important for assistive lower limb exoskeleton, and the task is realized mostly by the dynamics model or the EMG model. Although the dynamics model offers better estimation, it fails when unmodeled disturbances come into the system, such as the ground reaction force. In contrast, the EMG model is non-stationary, and therefore the offline calibrated EMG model is not satisfactory for long-time operation. In this paper, we propose the self-learning scheme with the sliding mode admittance control to overcome the deficiency. In the swing phase, the dynamics model is used to estimate the intention and teaches the EMG model; in the consecutive swing phase, the taught EMG model is used alternatively. In consequence, the self-learning control scheme provides better estimations during the whole operation. In addition, the admittance interface and the sliding mode controller ensure robust performance. The control scheme is justified by the knee orthosis with the backdrivable spring torsion actuator, and the experimental results are prominent.

Keywords: Agent-Based Systems, Autonomous Agents, Learning and Adaptive Systems
Abstract: Robust manipulation with tractability in unstructured environments is a prominent hurdle in robotics. Learning algorithms to control robotic arms have introduced elegant solutions to the complexities faced in such systems. A novel method of Reinforcement Learning (RL), Gaussian Process Dynamic Programming (GPDP), yields promissing results for closed-loop control of a low-cost manipulator however research surrounding most RL techniques lack breadth of comparable experiments into the viability of particular learning techniques on equivalent environments. We introduce several model-based learning agents as mechanisms to control a noisy, low-cost robotic system. The agents were tested in a simulated domain for learning closed-loop policies of a simple task with no prior information. Then, the fidelity of the simulations is confirmed by application of GPDP to a physical system.

Keywords: Learning and Adaptive Systems, Force Control, Human and humanoid skills/cognition/interaction
Abstract: This paper develops a learning control algorithm adapting the reference point and force to interact with an object of unknown geometry and elasticity. The controller is inspired by neuroscience studies that investigated the neural mechanisms when human adapt to virtual objects of different properties. The learning control algorithm estimates the shape and stiffness of the given object while maintaining a specified contact force with the environment. Simulations demonstrate the efficiency of the algorithm to identify the geometry and impedance of an unknown object without requiring force sensing. These properties are attractive for robotic haptic exploration with little demand on the sensing.

Keywords: Evolutionary Robotics, Legged Robots, Learning and Adaptive Systems
Abstract: An evolutionary computational approach for a gait generation of a quadruped robot autonomously generates a gait that adapts in an environment. In this approach, a fitness function that measures a performance of the gait is defined and parameters are optimized by maximizing or minimizing the function with evolutionary computation algorithms. However the previous research only has considered the optimization on an environment. In this paper, we suggest a gait adaptation method for a quadruped robot using a terrain classification and a gait optimization for an adaptation on various surfaces. The surfaces for the adaptation are learnt with a classification algorithm and a gait parameter on each surface is optimized with Particle Swarm Optimization (PSO). After the learning and the optimization, the classifier is used for classifying a surface that a robot is located and an optimized gait parameter is selected based on the classification result for the adaptation. The adaptation framework, a feature design and a filtering method for a classifier and a gait design for a quadruped robot are proposed in this paper. The proposed method was verified in a realistic 3D simulator and it successfully classified surfaces and selected optimized gaits for adaptations.

Keywords: Motion and Path Planning, Navigation, Search and Rescue Robots
Abstract: One milestone for autonomous mobile robotics is to endow robots with the capability to compute the plans and motor commands necessary to reach a defined goal position. For indoor or car-like robots moving on flat terrain, this problem is well mastered and open-source software can be deployed to such robots. However, for many applications such as search and rescue, ground robots must handle three-dimensional terrain. In this article, we present a system that is able to plan and execute a path in a complex environment. In order to cope with the complexity of a high-dimensional configuration space, we separate position and configuration planning. We demonstrate our system on a search and rescue robot with flippers by climbing up and down a difficult curved staircase.

Attachments: Video Attachment
Keywords: Nonholonomic Motion Planning, Integrated Planning and Control, Motion Control
Abstract: This paper deals with reactive and flexible human-like autonomous vehicle navigation. A human driver reactively guides his vehicle, performing a smooth trajectory within the roads limits until reaching the defined goal. To obtain a similar behavior with an unmanned ground vehicle (UGV), this paper proposes a flexible control law to drive a vehicle towards desired static or dynamic targets based on a novel definition of control variables and Lyapunov stability analysis. Moreover, a target assignment strategy, combined with an appropriate sigmoid function, that allow to perform smooth, flexible and safe vehicle navigation through successive waypoints is presented. The stability of the proposed control strategy is proved according to Lyapunov synthesis. Simulations and experiments are performed in different cases to demonstrate the reliability and efficiency of the control strategy.

Keywords: Nonholonomic Motion Planning, Omnidirectional Vision, SLAM
Abstract: This paper proposes a new method to estimate the 3D motion of a vehicle based on car-like structured motion model using an omnidirectional camera and a laser rangefinder. In recent years, motion estimation using vision sensor has improved by assuming planar motion in most conventional research to reduce requirement parameters and computational cost. However, for real applications in environment of outdoor terrain, the motion does not satisfy this condition. In contrast, our proposed method uses one corresponding image point and motion orientation to estimate the vehicle motion in 3D. In order to reduce requirement parameters for speedup computational systems, the vehicle moves under car-like structured motion model assumption. The system consists of a camera and a laser rangefinder mounted on the vehicle. The laser rangefinder is used to estimate motion orientation and absolute translation of the vehicle. An omnidirectional image-based one-point correspondence is used for combining with motion orientation and absolute translation to estimate rotation components of yaw, pitch angles and three translation components of Tx, Ty, and Tz. Real experiments in sloping terrain demonstrate the accuracy of vehicle localization estimation using the proposed method. The error at the end of travel position of our method, one-point RANSAC are 1.1%, 5.1%, respectively.

Keywords: Formal Methods in Robotics and Automation, Task Planning, Reactive and Sensor-Based Planning
Abstract: One increasingly popular approach for creating robot controllers for complex tasks is to automatically synthesize a hybrid controller from a high-level task specification. Such an approach, in addition to reducing the time and expertise required for creating a controller, guarantees that the robot will satisfy all of the underlying specifications, given perfect sensing and actuation. This paper investigates the probabilistic guarantees that can be made about the behavior of the robot when the actuation of the robot is no longer assumed to be perfect, as well as the possible specification revisions that can be made to improve the behavior of the robot. The approach described in this paper composes probabilistic models of the environment behavior and the robot actuation error with the synthesized controller, and uses probabilistic model checking techniques to find the probability that the robot satisfies a set of high level specifications. This paper also presents a preliminary approach for analyzing the composed model and automatically generating revisions to improve the robot's high-level behavior.

Keywords: Formal Methods in Robotics and Automation, Reactive and Sensor-Based Planning, Motion and Path Planning
Abstract: Applying correct-by-construction planning techniques to robots with complex nonlinear dynamics requires new formal analysis methods which guarantee that the requested behaviors can be achieved in the continuous space. In this paper, we construct low-level controllers that ensure the execution of a high-level mission plan. Controllers are generated using trajectory-based verification to produce a set of robust reach tubes which strictly guarantee that the required motions achieve the desired task specification. Reach tubes, computed here by solving a series of sum-of-squares optimization problems, are composed in such a way that all trajectories ensure correct high-level behaviors. We illustrate the new method using an input-limited unicycle robot satisfying task specifications expressed in linear temporal logic.

Keywords: Formal Methods in Robotics and Automation, Task Planning
Abstract: High-level robot control has recently seen the application of formal methods to the automatic synthesis of correct-by-construction controllers from user-defined specifications. When a specification fails to yield a corresponding controller, existing techniques provide feedback on portions of the specification that cause the failure, but at a coarse granularity. This work provides techniques for extracting minimal explanations of such failures. The approach is shown to provide refinement of the feedback on several example specifications.

Keywords: Space Robotics and Automation, Field Robots, Contact Modelling
Abstract: This paper presents the modeling and analysis of ciliary micro-hopping locomotion actuated by an eccentric motor, for enabling mobile robots to explore asteroids. Under the proposed system, elastic cilia are attached to the surface of the robot; this arrangement should enable the robot to have better mobility in a microgravity environment. However, in the development of the ciliary micro-hopping mechanism theoretical modeling and analysis of the interactive mechanics between the cilia and the environment pose technical challenges that need to be addressed. In this paper, we present the dynamics modeling of the ciliary micro-hopping locomotion actuated by an eccentric motor, along with its experimental validations and numerical simulations. The results of this study contribute to the design optimization of both the cilia mechanism and the motor control scheme.

Keywords: Space Robotics and Automation, Distributed Robot Systems, Localization
Abstract: This paper presents a new robot system consisting of plural small size rovers for an asteroid exploration. Each rover can communicate with others using radio, and a wireless mesh network is configured on an asteroid's surface. Our proposed system has the following three advantages against a conventional exploration system using one or two rovers: (1) It is possible to explore a wider area of an asteroid. (2) Since the mesh network has redundant communication paths, it has more robustness against some troubles. (3) It is possible to estimate the relative distances among plural rovers by using the mesh network. This relative distance estimation is useful for asteroid analyses using sensors that rovers have. Simulation results reveal the validity and effectiveness of our proposed rover system with the wireless mesh network and the relative distance estimation method.

Keywords: Space Robotics and Automation, Computer Vision, Field Robots
Abstract: Communication blackouts and latency are significant bottlenecks for planetary surface exploration; rovers cannot typically communicate during long traverses, so human operators cannot respond to unanticipated science targets discovered along the route. Targeted data collection by point spectrometers or high-resolution imagery requires precise aim, so it typically happens under human supervision during the start of each command cycle, directed at known targets in the local field of view. Spacecraft can overcome this limitation using onboard science data analysis to perform autonomous instrument targeting. Two critical target selection capabilities are the ability to target priority features of a known geologic class, and the ability to target anomalous surfaces that are unlike anything seen before.

This work addresses both challenges using probabilistic surface classification in traverse images. We first describe a method for targeting known classes in the presence of high measurement cost that is typical for power- and time-constrained rover operations. We demonstrate a Bayesian approach that abstains from uncertain classifications to significantly improve the precision of geologic surface classifications. Our results show a significant increase in classification performance, including a seven-fold decrease in misclassification rate for our random forest classifier. We then take advantage of these classifications and learned scene context in order to train a semi-supervised novelty detector. Operators can train the novelty detection to ignore known content from previous scenes, a critical requirement for multi-day rover operations. By making use of prior scene knowledge we find nearly a 100 percent increase in the number of abnormal features detected over comparable algorithms. We evaluate both of these techniques on a set of images acquired during field expeditions in the Mojave Desert.

Attachments: Video Attachment
Keywords: Space Robotics and Automation, New Actuators for Robotics
Abstract: In this paper we propose a new method to detumble a malfunctioning satellite. Large space debris such as malfunctioning satellites generally rotates with nutational motion. Thus several researches have proposed the methods to use a space robot for capturing and deorbiting these debris. The most of the past studies considered the method to detumble an uncontrollable satellite and then capture a single spinning satellite. However these methods require physical contact with malfunctioning satellites, which has a risk of accident. Therefore, we propose a method with an eddy current brake. The eddy current brake system can produce braking force to the target without any physical contact. Thus, we can reduce the risk of critical collision between the space robot and the target object. This paper firstly reviews dynamics of a tumbling satellite and proposes a detumbling strategy with the eddy current brake. We carry out a fundamental experiment to evaluate the performance of the braking force of the developed eddy current brake system, and then we simulate detumbling operation by using the experimental data and show an effectiveness of the proposed detumbling method.

Keywords: Space Robotics and Automation, Dynamics, Motion Control
Abstract: This paper discusses a vibration suppression control method for a space robot with a rigid manipulator and flexible appendage. A suitable dynamic model that considers the coupling between the manipulator and flexible appendage was developed for the controller to accomplish the vibration suppression control of the flexible appendage. The flexible appendage was modeled using a virtual joint model, and the control method was developed on the basis of this model. Although this type of control requires feedback of the flexible appendage state, its direct measurement is generally difficult. Thus, an estimator of the flexible appendage state was constructed using a force/torque sensor attached between the base and flexible appendage. The control method was experimentally verified using an air-floating system.

Keywords: Space Robotics and Automation, Redundant Robots, Path Planning for Manipulators
Abstract: The Canadarm2, also named pace Station Remote Manipulator System (SSRMS), is a 7-joint redundant manipulator. Without spherical wrists, the singularity analysis and avoidance of these manipulators are very difficult. In this paper, a method is presented to analytically identify its singular configurations based on the elementary transformation of Jacobian matrix. Firstly, we constructed a general kinematics model to describe them in a united manner. Correspondingly, the differential kinematics equation and the modified form are derived. Secondly, the singularity conditions are isolated and collected in a 3×4 sub-matrix by only four times row transformation of the modified Jacobian matrix, which is partitioned into a block-triangle matrix. Finally, all the singularity configurations are determined by analyzing the rank degeneracy conditions of the 3×4 sub-matrix. The proposed method isolates the singularity conditions, and collects them in a 3×4 sub-matrix, largely reducing the computation workload.

Keywords: Perception for Grasping and Manipulation, Force and Tactile Sensing, Biologically-Inspired Robots
Abstract: The manipulation of objects in a hand or gripper is typically accompanied by events such as slippage, between the fingers and a grasped object or between the object and external surfaces. Humans can identify such events using a combination of superficial and deep mechanoreceptors. In robotic hands, with more limited tactile sensing, such events can be hard to distinguish. This paper presents a signal processing method that can help to distinguish finger/object and object/world events based on multidimensional coherence, which measures whether a group of signals are sampling a single input or a group of incoherent inputs. A simple linear model of the fingertip/object interaction demonstrates how signal coherence can be used for slip classification. The method is evaluated through controlled experiments that produce similar results for two very different tactile sensing suites.

Keywords: Perception for Grasping and Manipulation, Personal Robots, Computer Vision
Abstract: Understanding positional semantics of the environment plays an important role in manipulating an object in clutter. The interaction with surrounding objects in the environment must be considered in order to perform the task without causing the objects fall or get damaged. In this paper, we learn the semantics in terms of support relationship among different objects in a cluttered environment by utilizing various photometric and geometric properties of the scene. To manipulate an object of interest, we use the inferred support relationship to derive a sequence in which its surrounding objects should be removed while causing minimal damage to the environment. We believe, this work can push the boundary of robotic applications in grasping, object manipulation and picking-from-bin, towards objects of generic shape and size and scenarios with physical contact and overlap. We have created an RGBD dataset that consists of various objects used in day-to-day life present in clutter. We explore many different settings involving different kind of object-object interaction. We successfully learn support relationships and predict support order in these settings.

Attachments: Video Attachment
Keywords: Perception for Grasping and Manipulation, Path Planning for Manipulators
Abstract: Mobile manipulators have brought a new level of flexibility to traditional automation tasks such as tabletop manipulation, but are not yet capable of the same speed and reliability as industrial automation. We present approaches to 3D perception and manipulator motion planning that enable a general purpose robotic platform to recognize and manipulate a variety of objects at a rate of one pick-and-place operation every 6.7s, and work with a conveyor belt carrying objects at a speed of 33 cm/s.

Keywords: Perception for Grasping and Manipulation, Computer Vision, Range Sensing
Abstract: Most current depth sensors provide 2.5D range images in which depth values are assigned to a rectangular 2D array. In this paper we take advantage of this structured information to build an efficient shape descriptor which is about two orders of magnitude faster than competing approaches, while showing similar performance in several tasks involving deformable object recognition. Given a 2D patch surrounding a point and its associated depth values, we build the descriptor for that point, based on the cumulative distances between their normals and a discrete set of normal directions. This processing is made very efficient using integral images, even allowing to compute descriptors for every range image pixel in a few seconds. The discriminative power of the resulting descriptor, dubbed FINDDD, is evaluated in three different scenarios: recognition of specific cloth wrinkles, instance recognition from geometry alone, and detection of reliable and informed grasping points.

Keywords: Perception for Grasping and Manipulation, Surgical Robotics, Sensor Fusion
Abstract: Real-time shape sensing and state acquisition is important for closed-loop control of hyper-redundant snake robots in minimally invasive surgery. Due to the miniaturized size of such minimally invasive surgery robots, it is not feasible to use existing angular sensors, such as the rotary encoders. With the advances of the MEMS technology, micro inertial sensor has shown its potential for robot state estimation. Previous studies have demonstrated that accurate joint angles can be estimated for one degree of freedom joints. However, more than one degree of freedom joints in the robot impose a number of challenges for the current joint angles estimation methods. This paper presents a micro-sensing platform and shape reconstruction algorithm for minimally invasive surgery snake robot with two degrees of freedom joints. The method incorporates gravitational and gyroscopic sensing by calculating the rotation difference between any consecutive robot segments. The gyroscope measurements are first used as the input to predict the rotation difference by direct orientation integration. The orientation difference is also derived from the consecutive acceleration vectors to update the prediction through a complementary filter. To demonstrate the performance of our proposed approach, a robot prototype with two universal joints was fabricated. Detailed experimental results have demonstrated that high accuracy can be achieved by using the proposed method for joint angles estimation.

Keywords: Perception for Grasping and Manipulation, Learning and Adaptive Systems, Visual Learning
Abstract: In this paper, we address the problem of inferring and manipulation deformable objects such as ropes. Starting with a RGBD view of the tangled rope, we first present a learning algorithm to infer the rope structure. We design appropriate features, an inference algorithm based on particle filters, and a learning algorithm based on max-margin learning. Then we reason about the knot structure of the rope, and choose an appropriate manipulation strategy based on current rope structure. We first perform extensive evaluation on offline datasets with five different rope types and 10 different knot types. In robotic experiments, we found that our bimanual manipulator (PR2) can untangle ropes successfully 76.9% of the time.

Attachments: Video Attachment
Keywords: Brain Machine Interface, Medical Systems, Healthcare, and Assisted Living, Human-Robot Interaction
Abstract: The development of new, light robotic systems has opened up a wealth of human–robot interaction applications. In particular, the use of robot manipulators as personal assistant for the disabled is realistic and affordable, but still requires research as to the brain-computer interface. Based on our previous work with tetraplegic individuals, we investigate the use of low-cost yet stable surface Electromyography (sEMG) interfaces for individuals with Spinal Muscular Atrophy (SMA), a disease leading to the death of neuronal cells in the anterior horn of the spinal cord; with sEMG, we can record remaining active muscle fibers. We show the ability of two individuals with SMA to actively control a robot in 3.5D continuously decoded through sEMG after a few minutes of training, allowing them to regain some independence in daily life. Although movement is not nearly as fast as natural, unimpaired movement, reach and grasp success rates are near 100% after 50 s of movement.

Attachments: Video Attachment
Keywords: Brain Machine Interface
Abstract: Recently, the Brain-Machine Interface (BMI) has been expected to be applied to robotics and medical science field as a new intuitive interface. BMI measures human cerebral activities and uses them directly as an input signal to various instruments. The future goal of our research is to design a practical BMI system that can be used reliably in daily lives. In this paper, we will discuss a design method of a BMI system using a portable Near-InfraRed Spectroscopy (NIRS) device and then we will consider improving the performance of the learning vector quantization (LVQ) classifier by using the independent component analysis (ICA) and the self-proliferating function of neurons. The effectiveness of the proposed method is investigated in human imagery classification experiments.

Keywords: Brain Machine Interface, Humanoid Robots
Abstract: Electrooculogram (EOG) signals are potential responses generated by eye movements, and event related potential (ERP) is a special electroencephalogram (EEG) pattern which evoked by external stimuli. Both EOG and ERP have been used separately for implementing human-machine interfaces which can assist disabled patients in performing daily tasks. In this paper, we present a novel EOG/ERP hybrid human-machine interface which integrates the traditional EOG and ERP interfaces together. Eye movements like the blink, wink, gaze, and frown are detected from EOG signals using double threshold algorithm. Multiple ERP components, i.e., N170, VPP and P300 are evoked by inverted face stimuli and classified by linear discriminant analysis (LDA). Based on this hybrid interface, we also design a control scheme for the humanoid robot NAO (Aldebaran robotics, Inc). On-line experiment results show that the proposed hybrid interface can effectively control the robot's basic movements and order it to make various behaviors. While normally operating the robot by hands takes 49.1 s to complete the experiment sessions, using the proposed EOG/ERP interface, the subject is able to finish the sessions in 54.1 s.

Keywords: Brain Machine Interface, Smart Infrastructures, Medical Systems, Healthcare, and Assisted Living
Abstract: The noninvasive brain-machine interface (BMI) is anticipated to be an effective tool of communication not only in laboratory settings but also in our daily livings. The direct communication channel created by BMI can assist aging societies and the handicapped and improve human welfare. In this paper we propose and experiment a BMI framework that combines BMI with a robotic house and autonomous robotic wheelchair. Autonomous navigation is achieved by placing waypoints within the house and, from the user side, the user performs BMI to give commands to the house and wheelchair. The waypoint framework can offer essential services to the user with an effectively improved information-transfer rate and is an excellent examples of the fusion of data measured by sensors in the house, which can offer insight into further studies.

Keywords: Brain Machine Interface, Medical Systems, Healthcare, and Assisted Living
Abstract: The present paper proposes an auditory BCI paradigm for systems based on P300 signals which are generated by auditory stimuli characterized by different sound typologies and locations. A Head Related Transfer Function approach is adopted to virtualize auditory stimuli. When virtualized audio is used, the user has to focus the attention both on the type and location of the stimulus, thus generating P300 signals whose amplitude is higher than that generated without audio virtualization. Classification is performed by Support Vector Machines in which gaussian radial basis functions are used as kernel functions. The system has been validated with 14 users, who were asked to choose one among five common spoken words, previously virtualized and transmitted to stereophonic headphones. Classification results prove that the proposed auditory BCI system performed similarly to common visual BCI P300 systems, representing then an alternative to visual BCI for users with visual impairments.

Attachments: Video Attachment
Keywords: Brain Machine Interface, Human-Robot Interaction, Telerobotics
Abstract: This paper presents the experimental validation of software-based safety features implemented during the control of a prosthetic limb in self-feeding tasks with a human patient. To ensure safe operation during patient controlled movements of the limb, velocity-based virtual fixtures are constructed with respect to the patient's location and orientation relative to the limb. These imposed virtual fixtures or safety zones modulate the allowable movement direction and speed of the limb to ensure patient safety during commanded limb trajectories directed toward the patient's body or environmental obstacles. In this implementation, the Modular Prosthetic Limb (MPL) will be controlled by a quadriplegic patient using implanted intracortical electrodes. These virtual fixtures leverage existing sensors internal to the MPL and operate in conjunction with the existing limb control. Validation of the virtual fixtures was conducted by executing a recorded set of limb control inputs while collecting both direct feedback from the limb sensors and ground truth measurements of the limb configuration using a Vicon tracking system. Analysis of the collected data indicates that the system performed within the limitations prescribed by the imposed virtual fixtures. This successful implementation and validation enabled the approved clinical use of the MPL system for a neural controlled self-feeding task.

Keywords: Localization, Marine Robotics
Abstract: This paper studies the underwater localization problem for a school of robotic fish, i.e., a kind of Autonomous Underwater Vehicles with limited size, power and payload. These robotic fish cannot be equipped with traditional underwater localization sensors that are big and heavy. The proposed localization system is performed by using a single surface mobile beacon which provides range measurement to bound the localization error. The main contribution of this paper lies in twofold: 1) Observability of single beacon based localization is first analyzed in the context of nonlinear discrete time system, deriving a sufficient condition on observability. 2) Moving Horizon Estimation is then integrated with Extended Kalman Filters for three-dimensional localization using single beacon, which can reduce the computational complexity, impose various constraints and make use of previous range measurements for current estimation. Extensive numerical simulations are conducted to verify the observability and high localization accuracy of the proposed underwater localization method.

Keywords: Localization, Neurorobotics, Aerial Robotics
Abstract: At the current state of the art, the agility of an autonomous flying robot is limited by its sensing pipeline, because the relatively high latency and low sampling frequency limit the aggressiveness of the control strategies that can be implemented. To obtain more agile robots, we need faster sensing pipelines. A Dynamic Vision Sensor (DVS) is a very different sensor than a normal CMOS camera: rather than providing discrete frames like a CMOS camera, the sensor output is a sequence of asynchronous timestamped events each describing a change in the perceived brightness at a single pixel. The latency of such sensors can be measured in the microseconds, thus offering the theoretical possibility of creating a sensing pipeline whose latency is negligible compared to the dynamics of the platform. However, to use these sensors we must rethink the way we interpret visual data. This paper presents a method for low-latency pose tracking using a DVS and Active Led Markers (ALMs), which are LEDs blinking at high frequency (>1 KHz). The sensor's time resolution allows distinguishing different frequencies, thus avoiding the need for data association. This approach is compared to traditional pose tracking based on a CMOS camera. The DVS performance is not affected by fast motion, unlike the CMOS camera, which suffers from motion blur.

Attachments: Video Attachment
Keywords: Localization, Computer Vision
Abstract: Relocalisation in 6D is relevant to a variety of Robotics applications and in particular to agile cameras exploring a 3D environment. While the use of geometry has commonly helped to validate appearance as a back-end process in several relocalisation systems before, we are interested in using 3D information to assist fast pose relocalisation computation as part of a front-end task. Our approach rapidly searches for a reduced number of visual descriptors, previously observed and stored in a database, that can be used to effectively compute the camera pose corresponding to the current view. We guide the search by means of constructing validated candidate sets using a 3D test involving the depth information obtained with an RGB-D camera (e.g. stereo of with structured light). Our experiments demonstrate that this process returns a compact quality set that works better for the pose estimation stage than when using a typical Nearest-Neighbor search over appearance only. The improvements are observed in terms of percentage of relocalised frames and speed, where the latter goes up to two orders of magnitude w.r.t. the conventional search.

Keywords: Localization, Sensor Networks
Abstract: Accuracy is a fundamental performance requirement in network localization. This paper studies the accuracy of range-based localization schemes for random sensor networks with respect to network connectivity and scale. We show that the variance of localization errors are proportional to average geometric dilution of precision (AGDOP). The paper proves a novel lower bound of expectation of DOP (LB-E-AGDOP). Our analysis based on LB-E-AGDOP shows that localization accuracy is approximately inversely proportional to the average degree of network. A further analysis shows that when network connectivity merely guarantees localizability, increasing sensor nodes leads to bounded monotonic increase in AGDOP; when a network is densely connected, increasing sensor nodes leads to bounded monotonic decrease in AGDOP. Finally, these conclusions are validated by numerical simulations.

Keywords: Localization, Mapping, Sensor Fusion
Abstract: The magnetic field in indoor environments is rich in features and exceptionally easy to sense. In conjunction with any form of odometry, such as signals produced from inertial sensors or wheel encoders, a map of this field can be used to precisely localize a human or robot in indoor environments. We show how the use of this field yields significant improvements in terms of localization accuracy and computational complexity for both legged and non-legged locomotion. We suggest various likelihood functions for sequential Monte Carlo localization and evaluate their performance based on magnetic maps of different quality. Specifically, we investigate the influence that measurement representation (e.g., intensity-based, vector-based) and map resolution have on localization accuracy, robustness, and complexity. Compared to other localization approaches (e.g., camera-based, LIDAR-based), there exist far fever privacy concerns when sensing the indoor environment's magnetic field. Furthermore, the required sensors are less costly, compact, and have a lower raw data rate and power consumption. The combination of technical and privacy-related advantages makes the use of the magnetic field a very viable solution to indoor navigation for both humans and robots.

Attachments: Video Attachment
Keywords: Localization, Computer Vision, Intelligent Transportation Systems
Abstract: Traditional vision-based localization methods such as visual SLAM suffer from practical problems in outdoor environments such as unstable feature detection and inability to perform location recognition under lighting, perspective, weather and appearance change. Additionally map construction on a large scale in these systems presents its own challenges. In this work, we present a novel method for precisely localizing vehicles on the road using signs marked on the road (road markings), which have the advantage of being distinct and easy to detect, their detection being robust under changes in lighting and weather. Our method uses corners detected on road markings to perform localization in global coordinates. The method consists of two phases - a mapping phase when a high-quality GPS device is used to automatically survey road marks and add them to a light-weight “map” or database, and a localization phase where road mark detection and look-up in the map, combined with visual odometry, produces precise localization. We present experiments using a real-time implementation operating in a car that demonstrates the improved localization robustness and accuracy of our system even when using road marks alone. However, in this case the trajectory between road marks has to be filled-in by visual odometry, which contributes drift. Hence, we also present a mechanism for combining road-mark-based maps with sparse feature-based maps that results in greater accuracy still. We see our use of road marks as a significant step in the general trend of using higher-level features for improved localization performance irrespective of environment conditions.

Keywords: Parallel Robots, Tendon/Wire Mechanism
Abstract: This paper addresses the simplification of cable model in static analysis of large-dimension cable-driven parallel robots (CDPR). An approach to derive a simplified hefty cable model is presented. The approach provides an insight into the limitation of such a simplification. The resulting cable tension computation is then used to solve the inverse kinematic problem of CDPR. A new expression of cable length taking into account both the non-negligible cable mass and elasticity is also introduced. Finally, simulations and experiments on a large CDPR prototype are provided. The results show that taking into account both cable mass and elasticity improves the robot accuracy.

Keywords: Tendon/Wire Mechanism, Biologically-Inspired Robots, Humanoid Robots
Abstract: This paper presents a design methodology for humanoid upper limb based on human anatomy. Kenshiro is a full body tendon driven humanoid robot and is designed from the data of average 14 year old Japanese boy. The design of his upper limb is realizing detail features of muscles, bones and the adhesive relation of the two. Human mimetic design is realized by focusing on the fact that joints are being stabled by muscles winding around the bones, and by accurately mimicking the bone shape this was enabled. In this paper we also introduce details of mechanical specifications of the upper limb. By having muscles, bones, and joint structures based on human anatomy, Kenshiro can move flexibly. The use as human body simulator can be expected by measuring sensor data which can correspond to bilogical data.

Keywords: Biologically-Inspired Robots, Underactuated Robots, Tendon/Wire Mechanism
Abstract: This paper presents a novel robot fish with vector propulsion. It can swim like a shark and/or a dolphin. The propulsor (tail) of the robot has an underactuated serpentine backbone and the actuation is done by two sets of orthogonally distributed wires. The backbone is composed of seven vertebras and an elastic rod. The vertebras are articulated by the rod and spherical joints. The horizontal flapping and vertical flapping are independently actuated by two motors. This enables the propulsor providing thrust in all directions. Propulsion model of the propulsor is developed by integrating the kinematic model and Lighthill’s elongated body theory. A prototype is built. Tests show that the robot fish could flap its tail like the shark or the dolphin effectively. In the swimming tests, the maximum swimming speed of the robot is 0.35 BL/s.

Keywords: Tendon/Wire Mechanism, Mechanism Design, Biomimetics
Abstract: Frictional influences in tendon-driven robotic systems are generally unwanted, with efforts towards minimizing them where possible. In the human hand however, the tendon-pulley system is found to be frictional with a difference between high-loaded static post-eccentric and post-concentric force production of 9-12% of the total output force. This difference can be directly attributed to tendon-pulley friction. Exploiting this phenomenon for robotic and prosthetic applications we can achieve a reduction of actuator size, weight and consequently energy consumption. In this study, we present the design of a bio-inspired friction switch. The adaptive pulley is designed to minimize the influence of frictional forces under low and medium-loading conditions and maximize it under high-loading conditions. This is achieved with a dual-material system that consists of a high-friction silicone substrate and low-friction polished steel pins. The system is described and its behavior experimentally validated with respect to the number and spacing of pins. The results validate its intended behavior, making it a viable choice for robotic tendon-driven systems.

Keywords: Kinematics, Nonholonomic Motion Planning, Parallel Robots
Abstract: This paper deals with the motion planning problem for parallel orienting platforms with one non-holonomic joint and two prismatic actuators which can maneuver to reach any three-degree-of-freedom pose of the moving platform. Since any system with two inputs and up to four generalized coordinates can always be transformed into chained form, this path planning problem can be solved using well-established procedures. Nevertheless, the use of these procedures requires a good understanding of Lie algebraic methods whose technicalities have proven a challenge to many practitioners who are not familiar with them. As an alternative, we show how by (a) properly locating the actuators, and (b) representing the platform orientation using Euler parameters, the studied path planning problem admits a closed-form solution whose derivation requires no other tools than ordinary linear algebra.

Keywords: Redundant Robots, Parallel Robots
Abstract: In this paper, we present an experimental eval- uation of the Cartesian stiffness of a novel parallel wrist under redundant and antagonistic actuation. The mechanism in consideration is Omni-Wrist V (OW5), a two degrees-of- freedom (DoF) parallel mechanism redundantly actuated by three subchains. We first give a brief review of its kineto- statics and derive its reduced Cartesian stiffness model. To illustrate the stiffness enhancement of OW5 under redundant and antagonistic actuation, its Cartesian stiffness is measured and evaluated under four control schemes: the non-redundant control, the minimum 2-norm torque control without or with redundant encoder, and the antagonistic actuation control. Measurement data are represented using stiffness matrices and stiffness ellipses. Our study offers a quick quantitative evaluation of stiffness enhancement of OW5 under redundant and antagonistic actuation.

Attachments: Video Attachment
Keywords: Rehabilitation Robotics, Motion Control, Medical Systems, Healthcare, and Assisted Living
Abstract: Various powered wearable lower limb exoskeletons are designed for paraplegics to make them walk again. Control methods are developed and implemented in these exoskeletons to provide active gait assistance in the sagittal plane while active control in the frontal plane is still missing. This paper proposed a control method that provided gait assistance in both lateral and sagittal plane. First, in the lateral plane, the exoskeleton was controlled to support the weight shift during stepping by providing assisting hip ab/adduction torques when the subject initiated a small amount of weight shift to the stance side to trigger a step. Second, the exoskeleton’s hip ab/adduction during stepping was controlled to improve lateral stability. This was achieved by altering the amount of hip ab/adduction to change step width at heel strike. Using these controls, an able-bodied subject could walk in the exoskeleton without any external balance aids, i.e. crutches or a walker, where his hip and knee joints were controlled by the exoskeleton and his ankle joints were constrained by the exoskeleton. The next step is to test whether the proposed method improves balance in spinal cord injured subjects.

Keywords: Hydraulic/Pneumatic Actuators, Medical Robots and Systems, Rehabilitation Robotics
Abstract: Soft actuators made of highly elastic polymers allow novel robotic system designs, yet application-specific soft robotic systems are rarely reported. Taking notice of the characteristics of soft pneumatic actuators (SPAs) such as high customizability and low inherent stiffness, we report in this work the use of soft pneumatic actuators for a biomedical use – the development of a soft robot for rodents, aimed to provide a physical assistance during gait rehabilitation of a spinalized animal. The design requirements to perform this unconventional task are introduced. Customized soft actuators, soft joints and soft couplings for the robot are presented. Live animal experiment was performed to evaluate and show the potential of SPAs for their use in the current and future biomedical applications.

Keywords: Rehabilitation Robotics, Motion Control, Medical Systems, Healthcare, and Assisted Living
Abstract: Recently, a large amount of stroke survivors are suffering from motor impairment. However, existed therapy interventions have limited effects to restore normal motor function. Thus, we proposed a novel control strategy for gait rehabilitation of hemiplegic patients. The whole system consists of a Functional Electrical Stimulation (FES) device and Treadmill-Walk system. FES contributes to improve the quality of the gait based on real-time adjustment of gait pattern. During gait, the electrical stimuli from separate output channels of an FES device are launched to stimulate two lower extremity muscles (Tibialis Anterior (TA) and Hamstrings). Stimulus launching procedure is based on identifying subject`s gait state (stance and swing phases). According to the current variation of treadmill motor, gait phase and muscle activation of lower limbs can be determined during walking on Treadmill-Walk. Three able-bodied subjects simulated hemiplegic patients in the experiment. The results indicated that the proposed method is a safe, feasible and promising intervention.

Keywords: Automation in Life Sciences: Biotechnology, Pharmaceutical and Health Care, Medical Systems, Healthcare, and Assisted Living, Rehabilitation Robotics
Abstract: In this paper we investigate the use of optimal control techniques to improve Functional Electrical Stimulation (FES) for drop foot correction on hemiplegic patients. A model of the foot and the tibialis anterior muscle, the contraction of which is controlled by electrical stimulation has been established and is used in the optimal control problem. The novelty in this work is the use of the ankle accelerations and shank orientations (so-called external states) in the model, which have been measured on hemiplegic patients in a previous experiment using Inertial Measurement Units (IMUs). The optimal control problem minimizes the square of muscle excitations which serves the overall goal of reducing energy consumption in the muscle. % and muscular fatigue. In a first step, an offline optimal control problem is solved for test purposes and shows the efficiency of the FES optimal control for drop foot correction. In a second step, a Nonlinear Model Predictive Control (NMPC) problem - or online optimal control problem, is solved in a simulated environment. While the ulitmate goal is to use NMPC on the real system, i.e. directly on the patient, this test in simulation was meant to show the feasibility of NMPC for online drop foot correction. In the optimization problem, a set of fixed constraints of foot orientation was applied. Then, an original adaptive constraint taking into account the current ankle height, was introduced and tested. Comparisons between results under fixed and adaptive constraints highlight the advantage of the adaptive constraints in terms of energy consumption, where its quadratic sum of controls, obtained by NMPC, was three times lower than with the fixed constraint.

This feasibility study was a first step in application of NMPC on real hemiplegic patients for online FES-based drop foot correction. The adaptive constraints method presents a new and efficient approach in terms of muscular energy consumption minimization.

Keywords: Medical Systems, Healthcare, and Assisted Living, Rehabilitation Robotics, Human Performance Augmentation
Abstract: This paper presents a new human-exoskeleton interaction approach to provide torque assistance of the lower limb movements upon wearer’s intention. The exoskeleton interacts with the wearer; the shank-foot orthosis system behaves as a second order dynamic system with gravity and elastic torque balance. The intention of the wearer is estimated by using a realistic musculoskeletal model of the muscles actuating the knee joint. The identification process concerns the inertial parameters of the shank-foot, the exoskeleton and the musculotendon parameters. Real-time experiments, conducted on a healthy subject during flexion and extension movements of the knee joint, have shown satisfactory results in terms of tracking error, intention detection and assistance torque generation. This approach guarantees asymptotic stability of the shank-foot-exoskeleton and adaptation to human-exoskeleton interaction. Moreover, the proposed control law is robust with respect to external disturbances.

Keywords: Rehabilitation Robotics, Physical Human-Robot Interaction, Force Control
Abstract: We present kinematics, actuation, detailed design, characterization results and initial user evaluations of AssistOn-Knee, a novel self-aligning active exoskeleton for robot-assisted knee rehabilitation. AssistOn-Knee can, not only assist flexion/extension movements of the knee joint but also accommodate its translational movements in the sagittal plane. Automatically aligning its joint axes, AssistOn-Knee enables an ideal match between human knee axis and the exoskeleton axis, guaranteeing ergonomy and comfort throughout the therapy. Self-aligning feature significantly shortens the setup time required to attach the patient to the exoskeleton, allowing more effective time spent on exercises. The proposed exoskeleton actively controls the rotational degree of freedom of the knee through a Bowden cable-driven series elastic actuator, while the translational movements of the knee joints are passively accommodated through use of a 3 degrees of freedom planar parallel mechanism. AssistOn-Knee possesses a light-weight and compact design with significantly low apparent inertia, thanks to its Bowden cable based transmission that allows remote location of the actuator and reduction unit. Furthermore, thanks to its series-elastic actuation, AssistOn-Knee enables high-fidelity force control and active backdriveability within its control bandwidth, while featuring passive elasticity for excitations above this bandwidth, ensuring safety and robustness throughout the whole frequency spectrum.

Keywords: Micro-manipulation, Mechanism Design, Manufacturing and production systems
Abstract: In this paper, we have described newly developed wet tweezers based on capillary force for micro-assembly of complex-shaped objects. The tweezers are composed of two movable rods driven by a piezoelectric linear motor and two thin tubes. The two rods penetrate the liquids in the thin tubes. If we simply stamp the rods on a base, we can apply a drop of even high viscosity liquids. If we contact them to an object, we can pick it up by capillary force. Because we use the pair of the rods for picking up, posture of objects are fixed. That is important for accurate micro-assembly. To investigate generative force of the wet tweezers, we study relationship among viscosity, surface tension, and shape of meniscus of the liquid. We also formulate the capillary force as a function of gap distance between the rod and the object with three different liquids. In several experiments, we have confirmed the wet tweezers have good assembling accuracy and possibility to realize heterogeneous and complex-shaped micro-assembly.

Keywords: Micro-manipulation, Micro/Nano Robots
Abstract: In this study, we present a new fixture (self-attachable fixture) and tensile test system for measuring mechanical properties of cell sheet. To evaluate strength of cell sheet, it is the most important to measure mechanical properties of tensile mode.　However, there has been no study which measured the tensile mechanical properties of cell sheet, since it has been difficult to attach a cell sheet in the tensile test system owing to the structure of the conventional fixture, and there has been no tensile test system which had a measurement range that covered the tension force range of the cell sheets. Therefore, we have addressed these problems by developing a self-attachable fixture and a tensile test system. By using developed system, we measured mechanical properties (tension, stress and initial stiffness) C2C12 of cell sheet cultured in different recipe of culture medium. The initial stiffness of cell sheet cultured in culture medium without FBS had a tendency to become stiffer. This indicates that our new fixture and test system are applicable for evaluating mechanical properties of cell sheets.

Attachments: Video Attachment
Keywords: Nano manipilation, Force and Tactile Sensing, Mapping
Abstract: Current methods of measuring mechanical properties at the micro-scale are destructive, and do not allow proper characterisation on resonant MEMS/NEMS. In this paper, a cartography of local stiffness variations on a suspended micromembrane is established for the first time, by a tuning-fork-based dynamic force sensor inside a SEM. Experiments are conducted on InP membranes 200nm thin, using a 9-DoF nano-manipulation system, complemented with virtual reality and automation tools. Results provide stiffness values ranging from 0.6 to 3 N/m on a single sample.

Keywords: Nano manipilation
Abstract: In this work we show that implementation of closed-loop control to silicon nanotweezers improves the sensitivity of the tool for mechanical characterization of biological molecules. Micromachined tweezers have already been used for the characterization of mechanical properties of DNA molecules as well as for the sensing of enzymatic reactions on DNA bundle. However the resolution of the experiments does not allow the sensing on single molecules. Hereafter we show theoretically and experimentally that, reducing the resonance frequency of the system by the implementation of a state feedback, the sensitivity to stiffness variation is enhanced. Such improvement leads to better resolution for detection of enzymatic reactions on DNA.

Keywords: Nano manufacturing, Nano manipilation
Abstract: We report the nanorobotic in situ forming and characterization of memristors based on individual copper oxide nanowires (CuO NWs) and their potential applications as nanosensors with memory (memristic sensors or “memsensors”). A series of in situ techniques for the experimental investigations of memristors are developed including nanorobotic manipulation, electro-beam-based forming, and electron energy loss spectroscopy (EELS) enabled correlation of transport properties and carrier distribution. All experimental investigations are performed inside a transmission electron microscope (TEM). The initial CuO NW memristors are formed by localized electron-beam irradiation to generate oxygen vacancies as dopants. Current-voltage properties show distinctive hysteresis characteristics of memristors. The mechanism of such memristic behaviors is explained with an oxygen vacancy migration model. The presence and migration of the oxygen vacancies is identified with EELS. Investigations also reveal that the memristic behavior can be influenced by the deformation of the nanowire, showing that the nanowire memristor can serve as a deformation/force memorable sensor. The CuO NW-based memristors will enrich the binary transition oxide family but hold a simpler and more compact design than the conventional thin-film version. With these advantages, the CuO NW-based memristors will not only facilitate their applications in nanoelectronics but play a unique role in micro-/nano-electromechanical systems (MEMS/NEMS) as well.

Keywords: SLAM, Localization, Mapping
Abstract: This paper reports on the use of generic linear constraint (GLC) node removal as a method to control the computational complexity of long-term simultaneous localization and mapping. We experimentally demonstrate that GLC provides a principled and flexible tool enabling a wide variety of complexity management schemes. Specifically, we consider two main classes: batch multi-session node removal, in which nodes are removed in a batch operation between mapping sessions, and online node removal, in which nodes are removed as the robot operates. Results are shown for 34.9 h of real- world indoor-outdoor data covering 147.4 km collected over 27 mapping sessions spanning a period of 15 months.

Attachments: Video Attachment
Keywords: SLAM, Marine Robotics, Field Robots
Abstract: This paper reports on the use of planar patches as features in a real-time simultaneous localization and mapping (SLAM) system to model smooth surfaces as piecewise-planar. This approach works well for using observed point clouds to correct odometry error, even when the point cloud is sparse. Such sparse point clouds are easily derived by Doppler velocity log sensors for underwater navigation. Each planar patch contained in this point cloud can be constrained in a factor-graph-based approach to SLAM so that neighboring patches are sufficiently coplanar so as to constrain the robot trajectory, but not so much so that the curvature of the surface is lost in the representation. To validate our approach, we simulated a virtual 6-degree of freedom robot performing a spiral-like survey of a sphere, and provide real-world experimental results for an autonomous underwater vehicle used for automated ship hull inspection. We demonstrate that using the sparse 3D point cloud greatly improves the self-consistency of the map. Furthermore, the use of our piecewise-planar framework provides an additional constraint to multi-session underwater SLAM, improving performance over monocular camera measurements alone.

Attachments: Video Attachment
Keywords: SLAM, Visual Tracking, Mapping
Abstract: In this work, a RGB-D input stream is utilized for GPU-boosted 3D reconstruction of textured indoor environments. The goal is to develop a process which produces standard 3D models from indoors to explore them virtually. Camera motion is tracked in 3D space by registering the current view with a reference view. Depending on the trajectory shape, the reference is either fetched from a concurrently built keyframe model or from a previous RGB-D measurement. Real-time tracking (30Hz) is executed on a low-end GPU, which is possible because structural data is not fused concurrently. After camera poses are estimated, both trajectory and structure are refined in post-processing. The global point cloud is compressed into triangulated surfaces by using Poisson reconstruction method, which is well-suited, because it fills holes and filters noise efficiently. Texturing is generated by backprojecting the nearest RGB image onto the watertight polygon mesh. The final model is stored in a standard 3D model format to allow easy user exploration and navigation in virtual 3D environment.

Attachments: Video Attachment
Keywords: Motion and Trajectory Generation, Unmanned Aerial Vehicles, Mapping
Abstract: This paper presents a novel algorithm capable of generating multiple next best views (NBVs), sorted by achievable information gain. Although being designed for waypoint generation in autonomous airborne mapping of outdoor environments, it works directly on raw point clouds and thus can be used with any sensor generating spatial occupancy information (e.g. LIDAR, kinect or Time-of-Flight cameras). To satisfy time-constraints introduced by operation on UAVs, the algorithm is implemented on a highly parallel architecture and benchmarked against the previous, CPU-based proof of concept. As the underlying hardware imposes limitations with regards to memory access and concurrency, necessary data structures and further performance considerations are explained in detail.

Open-source code for this paper is available at http://www.github.com/benadler/.

Attachments: Video Attachment
Keywords: Computer Vision, Unmanned Aerial Vehicles, SLAM
Abstract: We present a computationally inexpensive RGBD-SLAM solution taylored to the application on autonomous MAVs, which enables our MAV to fly in an unknown environment and create a map of its surroundings completely autonomously, with all computations running on its onboard computer. We achieve this by implementing efficient methods for both tracking its current location with respect to a heavily processed previously seen RGBD image (keyframe) and efficient relative registration of a set of keyframes using bundle adjustment with depth constraints as a front-end for pose graph optimization. We prove the accuracy and efficiency of our system based on a public benchmark dataset and demonstrate that the proposed method enables our quadrotor to fly autonomously.

Keywords: SLAM, Distributed Robot Systems, Networked Robots
Abstract: In this paper we describe a Simultaneous Localization and Mapping (SLAM) approach specifically designed to address the communication and computational issues that affect multi-robot systems. Our method utilizes condensed measurements to exchange map information between the robots. These measurements can effectively compress relevant portions of a map in a few data. This results in a substantial reduction of both the data to be transmitted and processed, that renders the system more robust and efficient. As documented by our simulated and real world experiments, these advantages come with a very little decrease in accuracy compared to ideal (but not realistic) methods that share the full data among all the robots.

Keywords: Computer Vision, Range Sensing, Distributed Robot Systems
Abstract: RGB-D sensors are becoming more and more vital to robotics. Sensors such as the Microsoft Kinect and time of flight cameras provide 3D colored point-clouds in real time can play a crucial role in Robot Vision. However these sensors suffer from precision deficiencies, and often the density of the point- clouds they provide is insufficient. In this paper, we present a multi-camera system for correction and enhancement of the data acquired from an RGB-D sensor. Our system consists of two sensors, the RGB-D sensor (main sensor) and a regular RGB camera (auxiliary sensor). We perform the correction and the enhancement of the data acquired from the RGB-D sensor by placing the auxiliary sensor in a close proximity to the target object and taking advantage of the established epipolar geometry. We have managed to reduce the relative error of the raw point-cloud from a Microsoft Kinect RGB-D sensor by 74.5 % and increase its density up to 2.5 times.

Attachments: Video Attachment
Keywords: Visual Tracking, Perception for Grasping and Manipulation, Range Sensing
Abstract: This paper presents a particle filtering approach for 6-DoF object pose tracking using an RGB-D camera. Our particle filter is massively parallelized in a modern GPU so that it exhibits real-time performance even with several thousand particles. Given an a priori 3D mesh model, the proposed approach renders the object model onto texture buffers on the GPU, and the rendered results are directly used by our parallelized likelihood evaluation. Both photometric (colors) and geometric (3D points and surface normals) features are employed to determine the likelihood of particles with respect to the given RGB-D scene. Our approach is compared with a tracker in the PCL both quantitatively and qualitatively in synthetic and real RGB-D sequences, respectively.

Keywords: Visual Tracking, Sensor Fusion, Calibration and Identification
Abstract: The advent of inexpensive RGB-D cameras brings new opportunities to capture a 3D environment. This paper presents a method to create a modular setup for generating a large 3D point cloud, with attention to the study of interference, the influence of a USB extension cable, and the calibration procedure. The study of interference includes the influence of the distance between the cameras, the orientation of the cameras, and the lightning. Furthermore, this paper proposes a number of evaluation metrics for similar setups.

Keywords: Computer Vision, Visual Navigation, SLAM
Abstract: In this paper we give an evaluation of different methods for computing frame-to-frame motion estimates for a moving RGB-D sensor, by means of aligning two images using photometric error minimization. These kind of algorithms have recently shown to be very accurate and robust and therefore provide an attractive solution for robot ego-motion estimation and navigation. We demonstrate three different alignment strategies, namely the Forward-Compositional, the Inverse-Compositional and the Efficient Second-Order Minimization approach, in a general robust estimation framework. We further show how estimating global affine illumination changes, in general improves the performance of the algorithms. We compare our results with recently published work, considered as state-of-the art in this field, and show that our solutions are in general more precise and can perform in real-time on standard hardware.

Keywords: Computer Vision, Visual Learning
Abstract: We introduce a method to discover objects from RGB-D image collections which does not require a user to specify the number of objects expected to be found. We propose a probabilistic formulation to find pairwise similarity between image segments, using a classifier trained on labelled pairs from the recently released RGB-D Object Dataset. We then use a correlation clustering solver to both find the optimal clustering of all the segments in the collection and to recover the number of clusters. Unlike traditional supervised learning methods, our training data need not be of the same class or category as the objects we expect to discover. We show that this parameter- free supervised clustering method has superior performance to traditional clustering methods.

Attachments: Video Attachment
Keywords: Visual Tracking, Computer Vision, Human detection and tracking
Abstract: In this paper, we propose a novel multiple object tracking method from RGB-D point set data by introducing the hierarchical spatiotemporal data association method (HSTA) in order to robustly track multiple objects without prior knowledge. HSTA is able to construct not only temporal associations between multiple objects, but also component-level spatiotemporal associations that allow the correction of falsely detected objects in the presence of various types of interaction among multiple objects. The proposed method was evaluated using the four representative interaction cases such as split, complete occlusion, partial occlusion, and multiple contacts. As a result, HSTA showed significantly more robust performance than did other temporal data association methods in the experiments.

Keywords: Robot Safety, Human-Humanoid Interaction, Physical Human-Robot Interaction
Abstract: The Human-Robot Interaction gets increasingly closer. In consequence, human safety has become a key issue for the success of the symbiosis between humans and robots. When the minimum distance between a human and a robot is too short, it can be naturally considered that the probability of a collision increases. Therefore, we consider that the robot should increase the distance to the human when the human is getting closer. We propose Withdrawal strategy as a method that aims to increase the distance by moving the end-effector not only away from the human but also to a parking position that can be previously assessed to be safer. To withdraw the end-effector, we use a virtual force model consisting of two virtual forces: a repelling force exerted by the human and an attractive force exerted by the parking position. We carry out experiments using a human-sized humanoid robot and five human subjects, and report the task completion time to evaluate the efficiency of the robot when performing a simple task.

Keywords: Robot Safety, Rehabilitation Robotics, Mechanism Design
Abstract: Safety is one of the most important issues in walking support robots. This paper presents a walking support robot equipped with velocity-based mechanical safety devices. The safety devices consist of only mechanical components without actuators, controllers, or batteries. The safety device is attached to each drive-shaft of the robot. If the safety device detects an unexpected angular velocity of the drive-shaft, the safety device can switch off all motors of the robot and lock the drive-shaft. The safety devices can work even if the robot's controller does not work. Firstly, we describe the characteristics of the safety device. Secondly, we explain the walking support robot and the structure and mechanism of the safety device. Thirdly, we show the walking support robot which we developed. Finally, we experimentally verify the effectiveness of the safety device.

Keywords: Robot Safety, Human-Robot Interaction, Industrial Robots
Abstract: In order to improve production flexibility, it is widely agreed that future working environments will be populated by both humans and robot manipulators, sharing the same workspace. This scenario introduces a series of safety issues which are uncommon in industrial settings where physical separation of robot areas is typically enforced. While several approaches for safe human-robot interaction exist, none of them can be easily integrated with production constraints. This paper discusses the composition of safety constraints with production ones. An algorithm is derived in order to maximize productivity, while guaranteeing a safe separation distance of the robot from the human. Experimental results showing the effectiveness of the approach in a typical industrial setting are also discussed.

Keywords: Robot Safety, Robotics in Hazardous Fields
Abstract: Robotic systems (RSs) are often used for performing critical tasks with little or no human intervention. Such RSs must satisfy certain dependability requirements including reliability, availability, security and safety. In this paper, we focus on the safety aspect and propose a methodology and associated framework for safety assessment of RSs in the early phases of development. The methodology relies upon model driven engineering approach and describes a preliminary safety assessment of safety-critical RSs using fault tree (FT) analysis (FTA). The framework supports a domain specific language for RSs called RobotML and includes facilities (i) to automatically generate or manually construct FTs and perform both qualitative and quantitative FTA, (ii) to make semantic connections with formal verification and FTA tools, (iii) to represent FTA results in the RobotML modeling environment. In the case study, we illustrate the proposed methodology and framework by considering a mobile robot developed in the scope of the Proteus project.

Keywords: Personal Robots, Human Performance Augmentation, Physical Human-Robot Interaction
Abstract: An approach for adaptive shared control of an assistive manipulator is presented. A set of distributed collision and proximity sensors is used to aid in limiting collisions during direct control by the disabled user. Artificial neural networks adapt the use of the proximity sensors online, which limits movements in the direction of an obstacle before a collision occurs. The system learns by associating the different proximity sensors to the collision sensors where collisions are detected. This enables the user and the robot to adapt simultaneously and in real-time, with the objective of converging on a usage of the proximity sensors that increases performance for a given user, robot implementation and task-set. The system was tested in a controlled setting with a simulated 5 DOF assistive manipulator and showed promising reductions in the mean time on simplified manipulation tasks. It extends earlier work by showing that the approach can be applied to full multi-link manipulators.

Attachments: Video Attachment
Keywords: Human-Robot Interaction, Sensor Networks, Force and Tactile Sensing
Abstract: In this paper we base upon capacitive tactile proximity sensor modules developed in a previous work to demonstrate applications for safe human-robot-interaction. Arranged as a matrix, the modules can be used to model events in the near proximity of the robot surface, closing the near field perception gap in robotics. The central application investigated here is object tracking. Several results are shown: the tracking of two human hands as well as the handling of occlusions and the prediction of collision for object trajectories. These results are important for novel pretouch- and touch-based human-robot interaction strategies and for assessing and implementing safety capabilities with these sensor systems.

Keywords: Human Centered Planning and Control, Humanoid Robots, Mobile Manipulation
Abstract: Human's action strategy is a good source of robot controller design. For there is no decisive criterion on balance control during manipulation tasks, human motion data are obtained and analyzed in this paper. Based on the observation of the center of mass (CoM) being proportional to target object distance but limited inside the supporting polygon, the bound-proportional CoM planner is proposed. Along with the CoM planner, whole-body balance and grasping controller for a dual-arm robot is suggested in a simple and computationally efficient structure. Dynamic simulation is conducted for validation, and showed competent results.

Keywords: Gesture, Posture, Social Spaces and Facial Expressions, Surveillance Systems, Visual Learning
Abstract: Computer vision as an entire field has a wide and diverse range of applications. The specific application for this project was in the realm of dance, notably ballet and choreography. This project was proof-of-concept for a choreography assistance tool used to recognize and record dance movements demonstrated by a choreographer. Keeping the commercial arena in mind, the Kinect from Microsoft was chosen as the imaging hardware, and a pilot set chosen to verify recognition feasibility. Before implementing a classifier, all training and test data was transformed to a more applicable representation scheme to only pass the important aspects to the classifier to distinguish moves for the pilot set. In addition, several classification algorithms using the Nearest Neighbor (NN) and Support Vector Machine (SVM) methods were tested and compared from a single dictionary as well as on several different subjects. The results were promising given the framework of the project, and several new expansions of this work are proposed.

Keywords: Human-Robot Interaction, Learning from Demonstration, Motion Control
Abstract: This article presents the current state of an ongoing work on Human Robot interaction in which two partners collaborate during an object hand-over interaction. The manipulator control is based on the Dynamic Movement Primitives model, specialized for the object hand-over context. The proposed modifications enable finer control of the dynamic of the DMP to align it to human control strategies, where the contributions of the feedforward and feedback parts of the control are slightly different than in the original DMP formulation. Furthermore, the proposed scheme handles moving goals. These two modifications combined, remove the requirement of an explicit estimation of the exchange position, allowing to generate the motion purely reactively given the instantaneous position of the human hand. The quality of the control system is evaluated through an extensive comparison with ground truth data related to the object interaction between two humans acquired in the context of the European project CogLaboration which envisages an application in an industrial setting.

Keywords: Gesture, Posture, Social Spaces and Facial Expressions
Abstract: This paper presents a 3D-point-cloud system that extracts a 3D-point-cloud feature (VISH) from the observation of a depth sensor to reduce feature/depth ambiguity and estimates human poses using the result of action classification and a kinematic model. Based on the concept of distributed representation, a non-parametric action-mixture model is proposed in the system to represent high-dimensional human-pose space using low-dimensional manifolds in searching human poses. In each manifold, the probability distribution is estimated by the similarity of features. The distributions in the manifolds are then redistributed according to the stationary distribution of a Markov chain that models the frequency of actions. After the redistribution, the manifolds are combined according to the distribution determined by the action classification. In addition, the spatial relationship between human-body parts is explicitly modeled by a kinematic chain. Computer-simulation results showed that multiple low-dimensional manifolds can represent human-pose space. The 3D-point-cloud system showed reduction of the overall error and standard deviation compared with other approaches without using action classification.

Keywords: Physical Human-Robot Interaction, Rehabilitation Robotics, Medical Robots and Systems
Abstract: Achieving coordination between a lower-limb exoskeleton and its user is challenging because walking is a dynamic process that involves multiple, precisely timed muscle activations. Electromyographical (EMG) feedback, in spite of its drawbacks, provides an avenue for assistance by enabling users to reduce the level of muscle activation required for walking. As an alternative to direct EMG feedback, we present a method for exoskeleton control based on learning the activation pattern of specific muscles during cyclic movements. Using the example of pendular leg motion, the torque profile of one muscle group (hip flexors) is learned in a two-step process. First, the estimated torque profile is indexed to the phase of the swing movement using an adaptive frequency oscillator (AFO). The profile is then encoded using linear weighted regression. In the algorithm's assistive mode, the learned profile is reconstructed by means of the AFO and without need for additional EMG input. The reconstructed profile is converted into a torque profile to be physically delivered by the exoskeleton. We tested our method on a single-actuator exoskeleton that assists the hip joint during stationary leg swing. The learning and assistance functions were built on top of an admittance controller that enhances the exoskeleton's mechanical transparency. Initial tests showed a high level of coordination, i.e. simultaneous positive work, between the subjects' hip flexor torque and the exoskeleton's assistive torque. This result opens the door for future studies to test the users' ability to reduce their muscle activation in proportion to the assistance delivered by the exoskeleton.

Keywords: Medical Systems, Healthcare, and Assisted Living, Human Performance Augmentation, Mechanism Design
Abstract: This study proposes a novel personal mobility vehicle for supporting and assisting people with disabled lower limbs. The developed mobile platform is capable of assisting voluntary postural transition between standing and sitting, called the Passively Assistive Limb (PAL) mechanism, in addition to high mobility with upright posture. The device consists of gas-spring-powered passive exoskeleton for postural support and two in-wheel motors for mobility support. The developed robot system allows a user to sit down on chairs and beds, and stand up through easy operations. In addition, a user can move the system in the standing posture without using their hands. In this paper, the development and assessments of the standing mobility vehicle are described.

Keywords: Mapping, Navigation
Abstract: In this paper we introduce a method for learning motion patterns in dynamic environments. Representations of dynamic environments have recently received an increasing amount of attention in the research community. Understanding dynamic environments is seen as one of the key challenges in order to enable autonomous navigation in real-world scenarios. However, representing the temporal dimension is a challenge yet to be solved. In this paper we introduce a spatial representation, which encapsulates the statistical dynamic behavior observed in the environment. The proposed Conditional Transition Map (CTMap) is a grid-based representation that associates a probability distribution for an object exiting the cell, given its entry direction. The transition parameters are learned from a temporal signal of occupancy on cells by using a local-neighborhood cross-correlation method. In this paper, we introduce the CTMap, the learning approach and present a proof-of-concept method for estimating future paths of dynamic objects, called Conditional Probability Propagation Tree (CPPTree). The evaluation is done using a real-world data-set collected at a busy roundabout.

Attachments: Video Attachment
Keywords: Learning and Adaptive Systems, Sensor-based Planning, AI Reasoning Methods
Abstract: In recent years, robots have been increasingly utilized in applications with complex unknown environments, which makes system modeling challenging. In order to meet the demand from such applications, an experience-based learning approach can be used. In this paper, a novel learning algorithm is proposed, which can learn an unknown system model from given data iteratively using a localization approach to manage the computational costs for real time applications. The algorithm segments the data domain by measuring significance of data. As case studies, the proposed algorithm is tested on the control of the mecanum-wheeled robot and in learning the inverse kinematics of a kinematically-redundant manipulator. As the result, the algorithm achieves the on-line system model learning for real time robotics applications.

Keywords: Learning and Adaptive Systems, Visual Learning
Abstract: Diffeomorphisms dynamical systems are dynamical systems where the state is an image and each commands induce a diffeomorphism of the state. These systems can approximate the dynamics of robotic sensorimotor cascades well enough to be used for problems such as planning in observations space. Learning of an arbitrary diffeomorphism from pairs of images is a high dimensional learning problem. Learning of an arbitrary diffeomorphism from pairs of images is an extremely high dimensional problem. The previous method had required O(ρ⁴) memory as a function of the desired resolution ρ, which, in practice, was the main limitation to the resolution of the diffeomorphisms that could be learned. This paper describes an algorithm based on recursive refinement that lowers the memory requirement to O(ρ²). Another improvement regards the estimation the diffeomorphism uncertainty, which is used to represent the sensor's limited field of view; the improved method obtains a more accurate estimation of the uncertainty by checking the consistency of a learned diffeomorphism and its independently learned inverse. The methods are tested on two robotic systems (a pan-tilt camera and a 5-DOF manipulator).

Keywords: Learning and Adaptive Systems, Learning from Demonstration, Motion and Trajectory Generation
Abstract: Nonlinear dynamical systems are a promising representation to learn complex robot movements. Besides their undoubted modeling power, it is of major importance that such systems work in a stable manner. We therefore present a neural learning scheme that estimates stable dynamical systems from demonstrations based on a two-stage process: first, a data-driven Lyapunov function candidate is estimated. Second, stability is incorporated by means of a novel method to respect local constraints in the neural learning. We show in two experiments that this method is capable of learning stable dynamics while simultaneously sustaining the accuracy of the estimate and robustly generates complex movements.

Keywords: Learning and Adaptive Systems, Adaptive Control, Integrated Task and Motion Planning
Abstract: This paper introduces Locally Weighted Least Squares Policy Iteration for learning approximate optimal control in settings where models of the dynamics and cost function are either unavailable or hard to obtain. Building on recent advances in Least Squares Temporal Difference Learning, the proposed approach is able to learn from data collected from interactions with a system, in order to build a global control policy based on localised models of the state-action value function. Evaluations are reported characterising learning performance for non-linear control problems including an under-powered pendulum swing-up task, and a robotic door-opening problem under different dynamical conditions.

Keywords: Learning and Adaptive Systems, Autonomous Agents, Failure Detection and Recovery
Abstract: Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot’s structure, sensors properties or end-effector position. This paper proposes a method to estimate a certain aspect of the forward kinematics model with no such information. An internal representation of the end-effector configuration is generated from unstructured proprioceptive and exteroceptive data flow under very limited assumptions. A mapping from the proprioceptive space to this representational space can then be used to control the robot.

Keywords: Motion and Path Planning
Abstract: Sampling-based algorithms have proven practical in solving motion planning challenges in relatively high-dimensional instances in geometrically complex workspaces. Early work focused on quickly returning feasible solutions. Only recently was it shown under which conditions these algorithms asymptotically return optimal or near-optimal solutions. These methods yield desired properties only in an asymptotic fashion, i.e., the properties are attained after infinite computation time. This work studies the finite-time properties of sampling-based planners in terms of path quality. The focus is on roadmap-based methods, due to their simplicity. This work illustrates that existing sampling-based planners, which construct roadmaps in an asymptotically (near-)optimal manner exhibit a "probably near-optimal" property in finite time. This means that it is possible to compute a confidence value, i.e. a probability, regarding the existence of upper bounds for the length of the path returned by the roadmap as a function of the number of configuration space samples. This property can result in useful tools for determining existence of solutions and a probabilistic stopping criterion for prm -like methods. These properties are validated through experimental trials.

Keywords: Motion and Path Planning, Collision Detection and Avoidance
Abstract: Configuration space plays an important role not only in motion planning but also in geometric modeling, shape and kinematic reasoning, and is fundamental to several basic geometric operations, such as continuous collision detection and generalized penetration depth estimation, that also find their applications in motion planning, animation and simulation. In this paper, we developed a new method for constructing the boundary of the CSpace obstacles (C-Obst) of polygons. This method is simpler to implement and often more efficient than the existing techniques. These main advantages are provided by a new algorithm that allows us to extract the Minkowski sum from the reduced convolution of the input polygons. We also developed a method for estimating the generalized penetration depth by computing the distance between the query point and the C-Obst surface.

Keywords: Motion and Path Planning
Abstract: Probabilistic Roadmap Methods (PRMs) are widely used motion planning methods that sample robot configurations (nodes) and connect them to form a graph (roadmap) containing feasible trajectories. Many variants propose different strategies for each of the steps and choosing among them is problem dependent. Planning in heterogeneous environments and/or on parallel machines necessitates dividing the problem into regions where these choices have to be made for each one. Hand-selecting the best method for each region becomes intractable. In particular, there are many ways to select connection candidates, and choosing the appropriate strategy is input dependent. In this paper, we present a general connection framework that adaptively selects a neighbor finding strategy from a candidate set of options. Our framework learns which strategy to use by examining their success rate and cost. It frees the user of the burden of selecting the best strategy and allows the selection to change over time. We perform experiments on rigid bodies of varying geometry and articulated linkages up to 37 degrees of freedom. Our results show that strategy performance is indeed problem/region dependent, and our adaptive method harnesses their strengths. Over all problems studied, our method differs the least from manual selection of the best method, and if one were to manually select a single method across all problems, the performance can be quite poor. Our method is able to adapt to changing sampling density and learns different strategies for each region when the problem is partitioned for parallelism.

Keywords: Motion and Path Planning
Abstract: Sampling-based probabilistic roadmap algorithms such as PRM and PRM* have been shown to be effective at solving certain motion planning problems, but the large graphs generated to express the connectivity and a metric on the configuration space may require much storage space and be expensive to search. Recent work by Marble and Bekris~cite{Marble2011a, Marble2011b} applied spanner algorithms to PRM*; these algorithms prune some edges in a dense graph, while guaranteeably maintaining an approximation to the metric. In this paper, we apply (and improve) a state-of-the-art streaming spanner algorithm to prune PRM* roadmaps. The algorithm we present has the main advantage of computational speed; when applied to PRM*, the processing time per vertex is independent of the number of sampled vertices, n, as compared to O(n log²(n) log(log(n)) ) in~cite{Marble2011b}. In practice, the algorithm we present prunes a graph with about 20 million edges in less than 20 seconds on a modern desktop computer; compared to the time required for generating such a roadmap, this additional processing time is essentially trivial. Because the combination of this algorithm with PRM* avoids many collision detections, the combination runs in several times faster than PRM*. We conduct experiments using OMPL, and analyze and compare the results to the results of existing sparse roadmap generation algorithms.

Attachments: Video Attachment
Keywords: Motion and Path Planning
Abstract: Probabilistic Roadmap Methods (PRMs) have been shown to work well at solving high Degree of Freedom (DoF) motion planning problems. They work by constructing a roadmap that approximates the topology of collisionfree configuration space. However, this requires an accurate model of the robot’s workspace in order to test if a sampled configuration is in collision or not. In this paper, we present a method for roadmap construction that can be used in workspaces with uncertainties in the model. For example, these can be inaccuracies that are caused by sensor error when an environment model was constructed. The uncertainty is encoded into the roadmap directly through the incorporation of non-binary collision detection values, e.g., a probability of collision. We refer to this new roadmap as a Safety-PRM because it allows tunability between the expected safety of the robot and the distance along a path. We compare the computational cost of Safety-PRM against two planning methods for environments without modeling errors, basic PRM and Medial Axis PRM(MAPRM), known for low computational cost and maximizing clearance, respectively. We demonstrate that in most cases, Safety-PRM produces high quality paths maximized for clearance and safety with the least amount of computational cost. We show that these paths are tunable for both robot safety and clearance. Finally, we demonstrate the applicability of Safety-PRM on an experimental system, a Barrett Whole Arm Manipulator (WAM). On the WAM, we demonstrate the mapping of expected collision to robot speeds to enable the robot to physically test the safety of the roadmap and use torque estimation to make roadmap modifications.

Keywords: Motion and Path Planning
Abstract: In sampling based motion planning algorithms the initial step at every iteration is to generate a new sample from the obstacle-free portion of the configuration space. This is usually accomplished via rejection sampling, i.e., repeatedly drawing points from the entire space until an obstacle-free point is found. This strategy is rarely questioned because the extra work associated with sampling (and then rejecting) useless points contributes at most a constant factor to the planning algorithm's asymptotic runtime complexity. However, this constant factor can be quite high in practice. We propose an alternative approach that enables sampling from a distribution that provably converges to a uniform distribution over only the obstacle-free space.

Our method works by storing empirically observed estimates of obstacle-free space in a point-proximity data structure, and then using this information to generate future samples. Both theoretical and experimental results validate our approach.