Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds
This addresses the challenge of sensitive open-loop grasping in robotics, offering a practical solution for applications like bin-picking and human-robot interaction, though it is incremental as it builds on existing imitation and reinforcement learning methods.
The paper tackles the problem of 6D robotic grasping in complex scenarios by proposing a closed-loop control policy that uses point clouds as input to output continuous 6D actions, improving grasping performance for unseen objects in tabletop and handover systems.
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, which are sensitive to grasp synthesis errors. In this work, we propose a new method for learning closed-loop control policies for 6D grasping. Our policy takes a segmented point cloud of an object from an egocentric camera as input, and outputs continuous 6D control actions of the robot gripper for grasping the object. We combine imitation learning and reinforcement learning and introduce a goal-auxiliary actor-critic algorithm for policy learning. We demonstrate that our learned policy can be integrated into a tabletop 6D grasping system and a human-robot handover system to improve the grasping performance of unseen objects. Our videos and code can be found at https://sites.google.com/view/gaddpg .