Learning Bipedal Robot Locomotion from Human Movement

TL;DR

This paper introduces a reinforcement learning approach for teaching a bipedal robot humanlike movements directly from motion capture data, enabling seamless transfer from simulation to real-world execution without additional training.

Contribution

The method integrates motion re-targeting and domain randomization to effectively transfer human motion to a robot, avoiding real-world training iterations.

Findings

Successfully transferred human motions to a robot in various tasks

Achieved safe and graceful failure modes during operation

Demonstrated real-world applicability without offline training

Abstract

Teaching an anthropomorphic robot from human example offers the opportunity to impart humanlike qualities on its movement. In this work we present a reinforcement learning based method for teaching a real world bipedal robot to perform movements directly from human motion capture data. Our method seamlessly transitions from training in a simulation environment to executing on a physical robot without requiring any real world training iterations or offline steps. To overcome the disparity in joint configurations between the robot and the motion capture actor, our method incorporates motion re-targeting into the training process. Domain randomization techniques are used to compensate for the differences between the simulated and physical systems. We demonstrate our method on an internally developed humanoid robot with movements ranging from a dynamic walk cycle to complex balancing and waving. Our controller preserves the style imparted by the motion capture data and exhibits graceful failure modes resulting in safe operation for the robot. This work was performed for research purposes only.