Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees
This work provides a method for generating coordinated robot motions for multi-task problems, which is significant for robotics researchers and practitioners dealing with complex robot control.
This paper addresses the challenge of generating robot motion for multiple simultaneous tasks by learning structured policies from human demonstrations. The proposed framework, inspired by RMPflow, allows users to specify relevant task spaces and design non-learned policies, resulting in stable motion generation validated on a 7-DOF Rethink Sawyer robot.
Generating robot motion that fulfills multiple tasks simultaneously is challenging due to the geometric constraints imposed by the robot. In this paper, we propose to solve multi-task problems through learning structured policies from human demonstrations. Our structured policy is inspired by RMPflow, a framework for combining subtask policies on different spaces. The policy structure provides the user an interface to 1) specifying the spaces that are directly relevant to the completion of the tasks, and 2) designing policies for certain tasks that do not need to be learned. We derive an end-to-end learning objective function that is suitable for the multi-task problem, emphasizing the deviation of motions on task spaces. Furthermore, the motion generated from the learned policy class is guaranteed to be stable. We validate the effectiveness of our proposed learning framework through qualitative and quantitative evaluations on three robotic tasks on a 7-DOF Rethink Sawyer robot.