Systems, Man, and Cybernetics

 

Home

• [P127] Data Acquisition and Modeling of 3D Deformable Objects using Neural Networks
  Author(s): Ana-Maria Cretu, Emil M. Petriu, Pierre Payeur
  
  

  Abstract
  The goal of the research presented in this paper is to develop a novel scheme for the measurement and the representation of deformable objects without a priori knowledge on their shape or material. The proposed solution advantageously combines a self-organizing map and feedforward neural network architectures to achieve diversified tasks as required for data collection on one side and the modeling of elastic characteristics on the other side. Data is collected for different objects using a joint sensing strategy that combines tactile probing and range imaging. Innovative object models are built as multi-resolution point-clouds associated with "tactile patches" and present certain advantages over classical deformable object models.

  
   

Full Text (PDF)