Motion Strategy Generation Based on Multimodal Motion Primitives and Reinforcement Learning Imitation for Quadruped Robots
Biomimetics · 04.02.2026 · 11 (2) · 115
DOI: 10.3390/biomimetics11020115 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 04.02.2026. Verfasst von Qin Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering, University of Jinan, Jinan 250022, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Key R&D Program of Shandong Province, China, Shandong Provincial Natural Science Foundation.
Abstract (Originalsprache)
With the advancement of task-oriented reinforcement learning (RL), the capability of quadruped robots for motion generation and complex task completion has significantly improved. However, current control strategies require extensive domain expertise and time-consuming design processes to acquire operational skills and achieve multi-task motion control, often failing to effectively manage complex behaviors composed of multiple coordinated actions. To address these limitations, this paper proposes a motion policy generation method for quadruped robots based on multimodal motion primitives and imitation learning. A multimodal motion library was constructed using 3D engine motion design, motion capture data retargeting, and trajectory planning. A temporal domain-based behavior planner was designed to combine these primitives and generate complex behaviors. We developed a RL-based imitation learning training framework to achieve precise trajectory tracking and rapid policy deployment, ensuring the effective application of actions/behaviors on the quadruped platform. Simulation and physical experiments conducted on the Lite3 quadruped robot validated the efficacy of the proposed approach, offering a new paradigm for the deployment and development of motion strategies for quadruped robots.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical Engineering, University of Jinan, Jinan 250022, China.
- School of Control Science and Engineering, Shandong University, Jinan 250061, China.
ORCID-Profile: Qin Zhang
Förderung
- National Key Research and Development Program of China
- Key R&D Program of Shandong Province, China
- Shandong Provincial Natural Science Foundation
Zitieren
APA
Zhang, Q., Li, G., Liu, B., Li, C., Zhu, C., & Chai, H. (2026). Motion Strategy Generation Based on Multimodal Motion Primitives and Reinforcement Learning Imitation for Quadruped Robots. Biomimetics, 11(2), 115. https://doi.org/10.3390/biomimetics11020115
Vancouver
Zhang Q, Li G, Liu B, Li C, Zhu C, Chai H. Motion Strategy Generation Based on Multimodal Motion Primitives and Reinforcement Learning Imitation for Quadruped Robots. Biomimetics. 2026;11(2):115. doi:10.3390/biomimetics11020115
BibTeX
@article{Zhang2026,
author = {Zhang, Qin and Li, Guanglei and Liu, Benhang and Li, Chenxi and Zhu, Chuanle and Chai, Hui},
title = {Motion Strategy Generation Based on Multimodal Motion Primitives and Reinforcement Learning Imitation for Quadruped Robots},
journal = {Biomimetics},
year = {2026},
volume = {11},
number = {2},
pages = {115},
doi = {10.3390/biomimetics11020115}
}
EUVIMED