Human Motion Control of Quadrupedal Robots using Deep Reinforcement Learning

TL;DR

This paper presents a novel deep reinforcement learning-based control system enabling human operators to intuitively command quadrupedal robots for diverse motor tasks, combining motion retargeting and imitation learning.

Contribution

It introduces a new motion control framework that retargets human motion to quadrupeds and employs curriculum learning for effective control policy development.

Findings

System enables various motor tasks on quadrupeds

Performance improved by training multiple experts

Effective in both simulated and real environments

Abstract

A motion-based control interface promises flexible robot operations in dangerous environments by combining user intuitions with the robot's motor capabilities. However, designing a motion interface for non-humanoid robots, such as quadrupeds or hexapods, is not straightforward because different dynamics and control strategies govern their movements. We propose a novel motion control system that allows a human user to operate various motor tasks seamlessly on a quadrupedal robot. We first retarget the captured human motion into the corresponding robot motion with proper semantics using supervised learning and post-processing techniques. Then we apply the motion imitation learning with curriculum learning to develop a control policy that can track the given retargeted reference. We further improve the performance of both motion retargeting and motion imitation by training a set of experts. As we demonstrate, a user can execute various motor tasks using our system, including standing, sitting, tilting, manipulating, walking, and turning, on simulated and real quadrupeds. We also conduct a set of studies to analyze the performance gain induced by each component.