Pretraining-finetuning Framework for Efficient Co-design: A Case Study on Quadruped Robot Parkour

TL;DR

This paper presents a pretraining-finetuning framework for co-optimizing mechanical structure and control policies in quadruped robots, significantly improving locomotive performance and efficiency for extreme parkour tasks.

Contribution

It introduces a novel co-design approach combining structure and control optimization with a new training method for enhanced generalizability.

Findings

Co-design outperforms traditional independent optimization methods.

Framework reduces time consumption in the design process.

Enhanced locomotive capabilities for quadruped robots in parkour scenarios.

Abstract

In nature, animals with exceptional locomotion abilities, such as cougars, often possess asymmetric fore and hind legs. This observation inspired us: could optimizing the leg length of quadruped robots endow them with similar locomotive capabilities? In this paper, we propose an approach that co-optimizes the mechanical structure and control policy to boost the locomotive prowess of quadruped robots. Specifically, we introduce a novel pretraining-finetuning framework, which not only guarantees optimal control strategies for each mechanical candidate but also ensures time efficiency. Additionally, we have devised an innovative training method for our pretraining network, integrating spatial domain randomization with regularization methods, markedly improving the network's generalizability. Our experimental results indicate that the proposed pretraining-finetuning framework significantly enhances the overall co-design performance with less time consumption. Moreover, the co-design strategy substantially exceeds the conventional method of independently optimizing control strategies, further improving the robot's locomotive performance and providing an innovative approach to enhancing the extreme parkour capabilities of quadruped robots.