Learning Fault-Tolerant Locomotion with Adaptive Gait Timing

2026-08-07

AI Summary

This work addresses the challenge of maintaining stable locomotion in large-scale quadrupedal robots under actuator failures by proposing an adaptive gait control method based on deep reinforcement learning. The approach employs an asymmetric Actor-Critic architecture, treating gait frequency as a learnable action dimension and incorporating a latent variable alignment loss to ensure representational consistency between the policy and value networks. This design enables joint adaptation to both actuator degradation and varying terrain conditions without requiring predefined failure-specific strategies. Experimental results demonstrate that the method effectively handles complex terrains in high-fidelity simulation and exhibits robustness and practicality when deployed on a real 68-kg quadruped robot.

Abstract

Hardware failures require legged robots to rapidly reorganize coordination and gait timing to maintain stability and mobility. This is particularly challenging for larger quadrupeds, where increased mass and tighter actuation limits reduce the feasibility of aggressive, high-frequency compensation strategies often observed on smaller platforms. In this work, we propose a deep reinforcement learning approach for fault-tolerant locomotion under actuator power loss. The method employs an asymmetric actor-critic architecture in which the critic has access to privileged information during training, while the actor learns to reconstruct a corresponding latent representation from proprioceptive observations. We introduce a latent-alignment loss that encourages consistency between actor and critic representations. Additionally, we augment the action space with a learnable gait frequency parameter, enabling adaptive gait timing in response to terrain variations and actuator degradation without predefined faulty-leg strategies. The approach is validated in high-fidelity simulation on uneven terrain and real-world experiments on flat ground using a 68 kg quadruped robot.

Problem

• fault-tolerant locomotion
• actuator failure
• adaptive gait timing
• quadruped robot
• hardware failures

Innovation

• fault-tolerant locomotion
• adaptive gait timing
• asymmetric actor-critic
• latent-alignment loss
• learnable gait frequency