Expressive Whole-Body Control for Humanoid Robots

TL;DR

This paper introduces Exbody, a reinforcement learning-based method enabling humanoid robots to generate expressive, diverse motions by learning from human motion data and transferring skills from simulation to real-world robots.

Contribution

The paper presents a novel whole-body control policy that combines imitation of human motions with relaxed constraints on legs, facilitating realistic and expressive robot behaviors in real environments.

Findings

Successful transfer of learned policies from simulation to real robots

Robots can perform diverse motions like walking, handshaking, and dancing

The approach outperforms baseline methods in realism and expressiveness

Abstract

Can we enable humanoid robots to generate rich, diverse, and expressive motions in the real world? We propose to learn a whole-body control policy on a human-sized robot to mimic human motions as realistic as possible. To train such a policy, we leverage the large-scale human motion capture data from the graphics community in a Reinforcement Learning framework. However, directly performing imitation learning with the motion capture dataset would not work on the real humanoid robot, given the large gap in degrees of freedom and physical capabilities. Our method Expressive Whole-Body Control (Exbody) tackles this problem by encouraging the upper humanoid body to imitate a reference motion, while relaxing the imitation constraint on its two legs and only requiring them to follow a given velocity robustly. With training in simulation and Sim2Real transfer, our policy can control a humanoid robot to walk in different styles, shake hands with humans, and even dance with a human in the real world. We conduct extensive studies and comparisons on diverse motions in both simulation and the real world to show the effectiveness of our approach.