Meta reinforcement learning for robust quadruped locomotion under joint failures
PLOS One · 2026
DOI: 10.1371/journal.pone.0361099 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Likai Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia. Hauptthemen laut MEDLINE: Joints, Robotics, Locomotion. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dezhou Engineering Research Center of Industrial Robot System Integration.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Electrical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia.
- School of Electrical Engineering, Shandong Huayu University of Technology, Dezhou, China.
- Department of Naval Architecture and Ocean Engineering, Pusan National University, Busan, South Korea.
ORCID-Profile: Likai Wu, Chee-Onn Chow
Förderung
- Dezhou Engineering Research Center of Industrial Robot System Integration
Zitieren
APA
Wu, L., Chow, C. O., Wong, W. R., Chuah, J. H., Kanesan, J., & Zhang, M. (2026). Meta reinforcement learning for robust quadruped locomotion under joint failures. PLOS One. https://doi.org/10.1371/journal.pone.0361099
Vancouver
Wu L, Chow CO, Wong WR, Chuah JH, Kanesan J, Zhang M. Meta reinforcement learning for robust quadruped locomotion under joint failures. PLOS One. 2026. doi:10.1371/journal.pone.0361099
BibTeX
@article{Wu2026,
author = {Wu, Likai and Chow, Chee-Onn and Wong, Wei Ru and Chuah, Joon Huang and Kanesan, Jeevan and Zhang, Meina},
title = {Meta reinforcement learning for robust quadruped locomotion under joint failures},
journal = {PLOS One},
year = {2026},
doi = {10.1371/journal.pone.0361099}
}
EUVIMED