2017/02/28 by Mabel M. Zhang, Nikolay Atanasov, Zhang, Mabel M. +3 · 1 citation
Computer Science · Engineering · #Artificial Intelligence in Games #FOS: Computer and information sciences #Human Pose and Action Recognition #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotics (cs.RO) #cs.RO
paper · pdf · doi:10.48550/arxiv.1703.00095
Accepted to International Conference on Intelligent Robots and Systems (IROS) 2017
openalex publication_date 2017/02/28 · arxiv created 2017/07/30 · arxiv updated 2017/08/01 · openalex created_date 2022/10/04 · openalex updated_date 2026/07/28
This paper considers the problem of active object recognition using touch only. The focus is on adaptively selecting a sequence of wrist poses that achieves accurate recognition by enclosure grasps. It seeks to minimize the number of touches and maximize recognition confidence. The actions are formulated as wrist poses relative to each other, making the algorithm independent of absolute workspace coordinates. The optimal sequence is approximated by Monte Carlo tree search. We demonstrate results in a physics engine and on a real robot. In the physics engine, most object instances were recognized in at most 16 grasps. On a real robot, our method recognized objects in 2--9 grasps and outperformed a greedy baseline.