Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds

6D robotic grasping beyond top-down bin-picking scenarios is a challenging task. Previous solutions based on 6D grasp synthesis with robot motion planning usually operate in an open-loop setting without considering perception feedback, dynamics, and contacts with objects, which makes them sensitive to grasp synthesis errors. In this work, we propose a novel method for learning closed-loop control policies for 6D robotic grasping using point clouds from an egocentric camera. We combine imitation learning and reinforcement learning in order to grasp unseen objects and handle the continuous 6D action space, where expert demonstrations are obtained from a joint motion and grasp planner. We introduce a goal-auxiliary actor-critic algorithm, which uses grasping goal prediction as an auxiliary task to facilitate policy learning. The supervision on grasping goals can be obtained from the expert planner for known objects or from hindsight goals for unknown objects. Overall, our learned closed-loop policy achieves over 90% success rates on grasping various ShapeNet objects and YCB objects in simulation. The policy also transfers well to the real world for grasping unseen objects in both a tabletop setting and a human-robot handover setting in our experiments. Our video can be found at https://sites.google.com/view/gaddpg .