Evolutionary Gait Reconfiguration in Damaged Legged Robots

TL;DR

This paper introduces a rapid, training-free algorithm that enables damaged legged robots to quickly reconfigure their gaits and restore locomotion, ensuring mission success despite physical impairments.

Contribution

It presents a novel damage recovery method using differential evolution that reconfigures leg gaits without prior training, achieving fast and robust recovery.

Findings

Restores locomotion in a hexapod within one hour

Effective reconfiguration of gaits after leg damage

High robustness to structural damage

Abstract

Multi-legged robots deployed in complex missions are susceptible to physical damage in their legs, impairing task performance and potentially compromising mission success. This letter presents a rapid, training-free damage recovery algorithm for legged robots subject to partial or complete loss of functional legs. The proposed method first stabilizes locomotion by generating a new gait sequence and subsequently optimally reconfigures leg gaits via a developed differential evolution algorithm to maximize forward progression while minimizing body rotation and lateral drift. The algorithm successfully restores locomotion in a 24-degree-of-freedom hexapod within one hour, demonstrating both high efficiency and robustness to structural damage.