본문 바로가기

Meta reinforcement learning for robust quadruped locomotion under joint failures

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q1
저널
PLOS ONE21(10) · #e0361099 · 2026
피인용
Web of Science 0Scopus 0
JCR IF
JCR 2024 2.6
ISSN
1932-6203

저자

  1. Wu, Likai제1저자Univ Malaya, Fac Engn, Dept Elect Engn, Kuala Lumpur, Malaysia
  2. Chow, Chee-Onn교신저자Univ Malaya, Fac Engn, Dept Elect Engn, Kuala Lumpur, Malaysia
  3. Wong, Wei RuUniv Malaya, Fac Engn, Dept Elect Engn, Kuala Lumpur, Malaysia
  4. Chuah, Joon HuangUniv Malaya, Fac Engn, Dept Elect Engn, Kuala Lumpur, Malaysia
  5. Kanesan, JeevanUniv Malaya, Fac Engn, Dept Elect Engn, Kuala Lumpur, Malaysia
  6. 장 메이나Pusan Natl Univ, Dept Naval Architecture & Ocean Engn, Busan, South Korea

초록

Joint failures can disrupt gait coordination, velocity tracking, and body stability in quadruped robots by reducing the available control authority. This study investigates faults in which joints remain locked at fixed angles and presents Adjudicate Reconfiguration and Evolving Regularization Meta Reinforcement Learning (ARER-MetaRL). The framework combines task inference from context, modular routing tailored to each task through an Adjudicate Reconfiguration (AR) network, and Evolving Gradient Regularization (ER) to support rapid adaptation. Tasks differ in the identities and locking angles of the faulty joints, the number of simultaneous faults, the commanded motion direction, and the terrain. Experiments in NVIDIA Isaac Sim cover all 12 actuated joints, with 0-3 stuck joints during meta-training and severity tests involving up to 6 simultaneously stuck joints. ARER-MetaRL achieves higher Mean Episode Linear Velocity Tracking Reward (MELV) and Mean Episode Roll-Pitch Tracking Reward (MERP) than single-task reinforcement learning, ablated variants, and the evaluated learning and adaptation baselines. Cumulative rewards further demonstrate the benefit of combining the proposed components. In the study of fault severity, ARER-MetaRL achieves MELV/MERP values of 0.86/0.84 with one stuck joint and 0.55/0.54 with six stuck joints, compared with 0.21/0.18 and 0.05/0.03, respectively, for the single-task baseline. These results show improved adaptation across different configurations of locked joints and terrain conditions.

키워드

FAULT-TOLERANT GAITSROBOT

식별자

Scopus EID
2-s2.0-105053769319
WoS UID
001906354200007