Robotic dexterous grasping is a challenging problem due to the high degree of freedom (DoF) and complex contacts of multi-fingered robotic hands. Existing deep reinforcement learning (DRL) based methods leverage human demonstrations to reduce sample complexity due to the high dimensional action space with dexterous grasping. However, less attention has been paid to hand-object interaction representations for high-level generalization. In this paper, we propose a novel geometric and spatial hand-object interaction representation, named DexRep, to capture dynamic object shape features and the spatial relations between hands and objects during grasping. DexRep comprises Occupancy Feature for rough shapes within sensing range by moving hands, Surface Feature for changing hand-object surface distances, and Local-Geo Feature for local geometric surface features most related to potential contacts. Based on the new representation, we propose a dexterous deep reinforcement learning method to learn a generalizable grasping policy DexRepNet. Experimental results show that our method outperforms baselines using existing representations for robotic grasping dramatically both in grasp success rate and convergence speed. It achieves a 93% grasping success rate on seen objects and higher than 80% grasping success rates on diverse objects of unseen categories in both simulation and real-world experiments.

翻译：机器人灵巧抓取因多指手的高自由度（DoF）和复杂接触而成为极具挑战性的问题。现有基于深度强化学习（DRL）的方法利用人类示教来降低灵巧抓取高维动作空间带来的样本复杂度，但对实现高层泛化的手-物交互表征关注不足。本文提出一种新颖的几何与空间手-物交互表征——DexRep，用于捕捉抓取过程中动态物体形状特征及手与物体间的空间关系。DexRep包含：通过手部移动感知粗糙形状的占用特征（Occupancy Feature）、表征手-物表面距离动态变化的表面特征（Surface Feature）、以及聚焦于潜在接触相关局部几何表面形态的局部几何特征（Local-Geo Feature）。基于该新型表征，我们提出一种灵巧深度强化学习方法，学习可泛化的抓取策略网络DexRepNet。实验结果表明，在抓取成功率与收敛速度两方面，本方法均显著优于基于现有表征的机器人抓取基线方法。在仿真与真实实验中，其对已知物体的抓取成功率达93%，对未知类别多样化物体的抓取成功率超80%。