Saving the Limping: Fault-tolerant Quadruped Locomotion via Reinforcement Learning

Modern quadrupeds are skillful in traversing or even sprinting on uneven terrains in a remote uncontrolled environment. However, survival in the wild requires not only maneuverability, but also the ability to handle potential critical hardware failures. How to grant such ability to quadrupeds is rar...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Liu, Dikai, Zhang, Tianwei, Yin, Jianxiong, See, Simon
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 07.09.2023
Subjects
Back injuries
Controllers
Deep learning
Fault tolerance
Locking
Locomotion
Maneuverability
Online AccessGet full text

Cover

More Information
Summary:Modern quadrupeds are skillful in traversing or even sprinting on uneven terrains in a remote uncontrolled environment. However, survival in the wild requires not only maneuverability, but also the ability to handle potential critical hardware failures. How to grant such ability to quadrupeds is rarely investigated. In this paper, we propose a novel methodology to train and test hardware fault-tolerant controllers for quadruped locomotion, both in the simulation and physical world. We adopt the teacher-student reinforcement learning framework to train the controller with close-to-reality joint-locking failure in the simulation, which can be zero-shot transferred to the physical robot without any fine-tuning. Extensive experiments show that our fault-tolerant controller can efficiently lead a quadruped stably when it faces joint failures during locomotion.
ISSN:2331-8422