EUVIMEDEUVIMED entdecken
Crossref

HLIP-Guided Reinforcement Learning for Agile Multigait Biped Locomotion

Yan Liu, Xizhe Zang, Xuehe Zhang, Chao Song, Boyang Chen, Yue Zhang, Jie Zhao

IEEE Transactions on Industrial Electronics · 2026-09 · 73 (9) · 13299-13310

DOI: 10.1109/tie.2026.3672828 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Industrial Electronics, 2026-09. Verfasst von Yan Liu und 6 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: State Key Laboratory of Robotics and Systems Special Program;, Harbin Institute of Technology Suzhou Research Institute Special Program on Humanoid Robots.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Humans can naturally switch between low-speed walking and high-speed running. For biped robots, this demands both multigait switching capability and high-speed motion performance. Imitation learning can readily generate diverse gaits using human motion data, but it is constrained by dataset quality and dynamic discrepancies between robots and humans, hindering the achievement of robust high-speed running. To address this limitation, we forgo human data and instead adopt a hybrid linear inverted pendulum (HLIP) as a dynamics prior: the HLIP generates nominal footholds and swing-leg trajectories online and in parallel, and these references are combined with reinforcement learning to guide exploration toward high-speed, multigait behaviors that better match the robot’s own dynamics. Specifically, we abstract the robot as a linear inverted pendulum and derive unified walking and running dynamics, yielding an HLIP that captures the key features of both gaits. Based on this model, a foothold planner is designed to generate nominal footholds. Then, a foothold tracking reward, in conjunction with other task-specific reward functions, is employed to guide the robot in exploring more stable high-speed multigait behaviors. We validate our approach on the 0.7-m-tall biped BRUCE, which seamlessly switches between walking and running on varied terrains, reaching 2.5 (simulation) and 1.8 m/s (hardware) top speeds. This hardware speed substantially exceeds the reported 0.6 m/s top speed of comparable sub-1 m bipeds, demonstrating that the learned policy concurrently acquires high-speed locomotion and multigait capabilities.

Förderung

  • State Key Laboratory of Robotics and Systems Special Program;
  • Harbin Institute of Technology Suzhou Research Institute Special Program on Humanoid Robots

Zitieren

APA

Liu, Y., Zang, X., Zhang, X., Song, C., Chen, B., Zhang, Y., & Zhao, J. (2026). HLIP-Guided Reinforcement Learning for Agile Multigait Biped Locomotion. IEEE Transactions on Industrial Electronics, 73(9), 13299-13310. https://doi.org/10.1109/tie.2026.3672828

Vancouver

Liu Y, Zang X, Zhang X, Song C, Chen B, Zhang Y, et al. HLIP-Guided Reinforcement Learning for Agile Multigait Biped Locomotion. IEEE Transactions on Industrial Electronics. 2026;73(9):13299-13310. doi:10.1109/tie.2026.3672828

BibTeX
@article{Liu2026,
  author = {Liu, Yan and Zang, Xizhe and Zhang, Xuehe and Song, Chao and Chen, Boyang and Zhang, Yue and Zhao, Jie},
  title = {HLIP-Guided Reinforcement Learning for Agile Multigait Biped Locomotion},
  journal = {IEEE Transactions on Industrial Electronics},
  year = {2026},
  volume = {73},
  number = {9},
  pages = {13299--13310},
  doi = {10.1109/tie.2026.3672828}
}
Kostenlos starten →