Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models

TL;DR

This paper introduces a hierarchical reinforcement learning framework utilizing generative models and animal motion data to enable quadrupedal robots to achieve lifelike agility, environmental adaptability, and complex task performance.

Contribution

It presents a novel hierarchical approach that leverages pre-trained generative models and multi-level knowledge to improve robotic agility and versatility beyond traditional methods.

Findings

Robots can mimic animal-like movements.

Enhanced obstacle traversal capabilities.

Successful multi-agent chase game performance.

Abstract

Knowledge from animals and humans inspires robotic innovations. Numerous efforts have been made to achieve agile locomotion in quadrupedal robots through classical controllers or reinforcement learning approaches. These methods usually rely on physical models or handcrafted rewards to accurately describe the specific system, rather than on a generalized understanding like animals do. Here we propose a hierarchical framework to construct primitive-, environmental- and strategic-level knowledge that are all pre-trainable, reusable and enrichable for legged robots. The primitive module summarizes knowledge from animal motion data, where, inspired by large pre-trained models in language and image understanding, we introduce deep generative models to produce motor control signals stimulating legged robots to act like real animals. Then, we shape various traversing capabilities at a higher level to align with the environment by reusing the primitive module. Finally, a strategic module is trained focusing on complex downstream tasks by reusing the knowledge from previous levels. We apply the trained hierarchical controllers to the MAX robot, a quadrupedal robot developed in-house, to mimic animals, traverse complex obstacles and play in a designed challenging multi-agent chase tag game, where lifelike agility and strategy emerge in the robots.