Learning-Based Fault Detection for Legged Robots in Remote Dynamic Environments

2026-04-03

AI Summary

This study addresses the challenge of autonomous fault identification and adaptive locomotion in quadrupedal robots operating in remote, dynamic environments, where undetected limb damage can lead to mission failure or structural destruction. The authors propose an offline learning–based fault detection method that leverages proprioceptive data—such as joint angles and torques—to accurately identify single-limb failures and trigger an adaptive switch in the controller to a tripod gait suited to the robot’s altered morphology. By integrating learned fault diagnosis with context-aware tripod gait selection for the first time, this approach significantly enhances post-damage locomotion robustness and enables sustained operation in complex, hazardous terrains.

Abstract

Operations in hazardous environments put humans, animals, and machines at high risk for physically damaging consequences. In contrast to humans and animals, quadruped robots cannot naturally identify and adjust their locomotion to a severely debilitated limb. The ability to detect limb damage and adjust movement to a new physical morphology is the difference between survival and death for humans and animals. The same can be said for quadruped robots autonomously carrying out remote assignments in dynamic, complex settings. This work presents the development and implementation of an off-line learning-based method to detect single limb faults from proprioceptive sensor data in a quadrupedal robot. The aim of the fault detection technique is to provide the correct output for the controller to select the appropriate tripedal gait to use given the robot's current physical morphology.

Problem

• fault detection
• legged robots
• limb damage
• proprioceptive sensing
• adaptive locomotion

Innovation

• learning-based fault detection
• quadruped robots
• proprioceptive sensing
• adaptive locomotion
• tripedal gait