Entropy-based motion selection for touch-based registration using Rao-Blackwellized particle filtering

Y. Taguchi, T. K. Marks, J. R. Hershey
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Registering an object with respect to a robot's coordinate system is essential to industrial assembly tasks such as grasping and insertion. Touch-based registration algorithms use a probe attached to a robot to measure the positions of contact, then use these measurements to register the robot to a model of the object. In existing work on touch-based registration, the selection of contact positions is not typically addressed. We present an algorithm for selecting the next robot motion to
more » ... e the expected information obtained by the resulting contact with the object. Our method performs 6-DOF registration in a Rao-Blackwellized particle filtering (RBPF) framework. Using the 3D model of the object and the current RBPF distribution, we compute the expected information gain from a proposed robot motion by estimating the expected entropy that the RBPF distribution would have as a result of being updated by the proposed motion. The motion that provides the maximum information gain is selected and used for the next measurement, and the process is repeated. We compare various methods for estimating entropy, including approximations based on kernel density estimation. We demonstrate entropy-based motion selection in fully automatic and human-guided registration, both in simulations and on a real robotic platform. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. Abstract-Registering an object with respect to a robot's coordinate system is essential to industrial assembly tasks such as grasping and insertion. Touch-based registration algorithms use a probe attached to a robot to measure the positions of contact, then use these measurements to register the robot to a model of the object. In existing work on touch-based registration, the selection of contact positions is not typically addressed. We present an algorithm for selecting the next robot motion to maximize the expected information obtained by the resulting contact with the object. Our method performs 6-DOF registration in a Rao-Blackwellized particle filtering (RBPF) framework. Using the 3D model of the object and the current RBPF distribution, we compute the expected information gain from a proposed robot motion by estimating the expected entropy that the RBPF distribution would have as a result of being updated by the proposed motion. The motion that provides the maximum information gain is selected and used for the next measurement, and the process is repeated. We compare various methods for estimating entropy, including approximations based on kernel density estimation. We demonstrate entropy-based motion selection in fully automatic and human-guided registration, both in simulations and on a real robotic platform.
doi:10.1109/iros.2011.6048375 fatcat:63sgwhfczrhdnefstcmiv7awrm