Learning Agile Robotic Locomotion Skills by Imitating Animals

TL;DR

This paper introduces an imitation learning system enabling legged robots to acquire diverse agile locomotion skills by mimicking animals, using reference data and domain adaptation for efficient simulation training and real-world deployment.

Contribution

It presents a unified imitation learning approach that automatically synthesizes controllers for multiple behaviors, reducing manual design effort and enhancing adaptability in legged robots.

Findings

Successfully trained an 18-DoF quadruped to perform various agile behaviors

Achieved rapid transfer from simulation to real-world robot control

Demonstrated diverse locomotion skills including gaits, hops, and turns

Abstract

Reproducing the diverse and agile locomotion skills of animals has been a longstanding challenge in robotics. While manually-designed controllers have been able to emulate many complex behaviors, building such controllers involves a time-consuming and difficult development process, often requiring substantial expertise of the nuances of each skill. Reinforcement learning provides an appealing alternative for automating the manual effort involved in the development of controllers. However, designing learning objectives that elicit the desired behaviors from an agent can also require a great deal of skill-specific expertise. In this work, we present an imitation learning system that enables legged robots to learn agile locomotion skills by imitating real-world animals. We show that by leveraging reference motion data, a single learning-based approach is able to automatically synthesize controllers for a diverse repertoire behaviors for legged robots. By incorporating sample efficient domain adaptation techniques into the training process, our system is able to learn adaptive policies in simulation that can then be quickly adapted for real-world deployment. To demonstrate the effectiveness of our system, we train an 18-DoF quadruped robot to perform a variety of agile behaviors ranging from different locomotion gaits to dynamic hops and turns.