Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors
This work addresses the challenge of reducing reward engineering for robot control, making it easier to deploy natural-looking behaviors on real hardware, though it is incremental as it builds on prior imitation methods.
The paper tackles the problem of learning reusable locomotion skills for legged robots by imitating human and animal motion capture data, resulting in policies for walking and ball dribbling that transfer zero-shot to real robots like ANYmal and OP3.
We investigate the use of prior knowledge of human and animal movement to learn reusable locomotion skills for real legged robots. Our approach builds upon previous work on imitating human or dog Motion Capture (MoCap) data to learn a movement skill module. Once learned, this skill module can be reused for complex downstream tasks. Importantly, due to the prior imposed by the MoCap data, our approach does not require extensive reward engineering to produce sensible and natural looking behavior at the time of reuse. This makes it easy to create well-regularized, task-oriented controllers that are suitable for deployment on real robots. We demonstrate how our skill module can be used for imitation, and train controllable walking and ball dribbling policies for both the ANYmal quadruped and OP3 humanoid. These policies are then deployed on hardware via zero-shot simulation-to-reality transfer. Accompanying videos are available at https://bit.ly/robot-npmp.