TOLEBI: Learning Fault-Tolerant Bipedal Locomotion via Online Status Estimation and Fallibility Rewards

2026-02-05

AI Summary

This work proposes the first learning-based fault-tolerant control framework for bipedal locomotion to address motion instability caused by hardware failures such as joint lock-up, power loss, or external disturbances. By injecting diverse failure modes during simulation and integrating online joint state estimation with a fault-aware reward mechanism, the framework trains a reinforcement learning policy capable of real-time adaptation. The resulting locomotion strategy successfully transfers from simulation to a physical robot without further fine-tuning. Experiments on the TOCABI humanoid demonstrate that the proposed approach significantly enhances motion stability and robustness under unexpected hardware faults, validating its effectiveness in handling multiple types of real-world failures in dynamic environments.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

With the growing employment of learning algorithms in robotic applications, research on reinforcement learning for bipedal locomotion has become a central topic for humanoid robotics. While recently published contributions achieve high success rates in locomotion tasks, scarce attention has been devoted to the development of methods that enable to handle hardware faults that may occur during the locomotion process. However, in real-world settings, environmental disturbances or sudden occurrences of hardware faults might yield severe consequences. To address these issues, this paper presents TOLEBI (A faulT-tOlerant Learning framEwork for Bipedal locomotIon) that handles faults on the robot during operation. Specifically, joint locking, power loss and external disturbances are injected in simulation to learn fault-tolerant locomotion strategies. In addition to transferring the learned policy to the real robot via sim-to-real transfer, an online joint status module incorporated. This module enables to classify joint conditions by referring to the actual observations at runtime under real-world conditions. The validation experiments conducted both in real-world and simulation with the humanoid robot TOCABI highlight the applicability of the proposed approach. To our knowledge, this manuscript provides the first learning-based fault-tolerant framework for bipedal locomotion, thereby fostering the development of efficient learning methods in this field.

Problem

• fault-tolerant locomotion
• bipedal walking
• hardware faults
• external disturbances
• online status estimation

Innovation

• fault-tolerant locomotion
• online status estimation
• reinforcement learning
• sim-to-real transfer
• bipedal robotics