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

TL;DR

This paper introduces TOLEBI, a novel learning framework that enables bipedal robots to perform fault-tolerant locomotion by incorporating online status estimation and fallibility rewards, validated through real-world and simulation experiments.

Contribution

It presents the first learning-based fault-tolerant framework for bipedal locomotion, integrating online joint status classification and sim-to-real transfer.

Findings

Successful fault-tolerant locomotion in simulation and real-world tests

Effective classification of joint conditions during operation

Enhanced robustness against hardware faults and disturbances

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.