TWIST: Teleoperated Whole-Body Imitation System
This addresses the challenge of achieving versatile and coordinated whole-body control in humanoid robots, which is incremental by improving upon existing teleoperation methods.
The paper tackles the problem of teleoperating humanoid robots for whole-body coordinated behavior by introducing TWIST, a system that uses retargeted human motion capture data and a reinforcement learning plus behavior cloning controller, enabling robots to perform diverse skills like manipulation and locomotion with a single neural network.
Teleoperating humanoid robots in a whole-body manner marks a fundamental step toward developing general-purpose robotic intelligence, with human motion providing an ideal interface for controlling all degrees of freedom. Yet, most current humanoid teleoperation systems fall short of enabling coordinated whole-body behavior, typically limiting themselves to isolated locomotion or manipulation tasks. We present the Teleoperated Whole-Body Imitation System (TWIST), a system for humanoid teleoperation through whole-body motion imitation. We first generate reference motion clips by retargeting human motion capture data to the humanoid robot. We then develop a robust, adaptive, and responsive whole-body controller using a combination of reinforcement learning and behavior cloning (RL+BC). Through systematic analysis, we demonstrate how incorporating privileged future motion frames and real-world motion capture (MoCap) data improves tracking accuracy. TWIST enables real-world humanoid robots to achieve unprecedented, versatile, and coordinated whole-body motor skills--spanning whole-body manipulation, legged manipulation, locomotion, and expressive movement--using a single unified neural network controller. Our project website: https://humanoid-teleop.github.io