Robust Quadruped Locomotion via Reinforcement Learning with Deep Generalized-Momentum-Based Kalman Filter
Electronics · 08.06.2026 · 15 (12) · 2528
DOI: 10.3390/electronics15122528 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 08.06.2026. Verfasst von Jingyu Sun und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation for Distinguished Young Scholars of Shandong Provinc.
Abstract (Originalsprache)
Robust quadruped locomotion in real-world environments remains challenging because external disturbances, sensor noise, and model uncertainties are coupled with intermittent foot–ground contact. Reinforcement learning has shown strong capability in generating agile locomotion, but many existing methods handle unobserved disturbances through implicit latent representations or domain randomization. This paper presents a disturbance-aware locomotion framework that integrates state and disturbance estimation with learning-based control. The core component is a deep generalized-momentum-based Kalman filter, which combines generalized momentum disturbance modeling with adaptive covariance inference to estimate the base velocity and external disturbance force. These physically meaningful estimates are incorporated into the policy observation space, reducing the gap between privileged simulation states and deployable onboard observations. The framework was evaluated in a simulation and on a quadruped robot platform under disturbance and outdoor locomotion scenarios. Compared with the baseline and ablated variants, the proposed method reduced estimation and tracking errors, limited impact-induced torque peaks, and improved locomotion success rates under the evaluated conditions. The results suggest that explicit disturbance estimation can complement a latent adaptation for quadruped locomotion under impact-rich conditions.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation for Distinguished Young Scholars of Shandong Provinc
Zitieren
APA
Sun, J., Wang, Z., Li, Y., & Zhou, L. (2026). Robust Quadruped Locomotion via Reinforcement Learning with Deep Generalized-Momentum-Based Kalman Filter. Electronics, 15(12), 2528. https://doi.org/10.3390/electronics15122528
Vancouver
Sun J, Wang Z, Li Y, Zhou L. Robust Quadruped Locomotion via Reinforcement Learning with Deep Generalized-Momentum-Based Kalman Filter. Electronics. 2026;15(12):2528. doi:10.3390/electronics15122528
BibTeX
@article{Sun2026,
author = {Sun, Jingyu and Wang, Zixuan and Li, Yibin and Zhou, Lelai},
title = {Robust Quadruped Locomotion via Reinforcement Learning with Deep Generalized-Momentum-Based Kalman Filter},
journal = {Electronics},
year = {2026},
volume = {15},
number = {12},
pages = {2528},
doi = {10.3390/electronics15122528}
}
EUVIMED