Active end-effector pose selection for tactile object recognition through Monte Carlo tree search
Active end-effector pose selection for tactile object recognition through Monte Carlo tree search
复制标题
通过蒙特卡罗树搜索进行触觉物体识别的主动末端执行器姿势选择
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Kostas Daniilidis
中科院分区：
文献类型：
--
作者：
Mabel M. Zhang;Nikolay A. Atanasov;Kostas Daniilidis
本文考虑的问题，仅使用触摸的主动物体识别。重点是自适应地选择一系列的手腕姿势，实现准确的识别外壳把握。它旨在最大限度地减少触摸次数并最大限度地提高识别信心。这些动作被公式化为手腕相对于彼此的姿势，使得算法独立于绝对工作空间坐标。最优序列近似的蒙特卡洛树搜索。我们展示了结果在物理引擎和一个真实的机器人。在物理引擎中，大多数对象实例在最多16次抓握中被识别。在真实的机器人上，我们的方法可以在2-9次抓取中识别物体，并且性能优于贪婪基线。
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.