EUVIMEDEUVIMED entdecken
Crossref

Curriculum-Enhanced Reinforcement Learning for Robust Humanoid Locomotion

Yi Zhou, Jianbin Qiu, Shixiang Jia, Fenglei Ni, Wei Zhang

IEEE Transactions on Automation Science and Engineering · 2026 · 23 · 5779-5789

DOI: 10.1109/tase.2026.3669985 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Automation Science and Engineering, 2026. Verfasst von Yi Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The control of humanoid locomotion remains one of the most formidable challenges in robotics. Conventional model-based approaches not only rely extensively on manual design but also exhibit limited generalization across diverse tasks and environments. To overcome these limitations, a curriculum-enhanced reinforcement learning framework is proposed in this work for training robust locomotion. Given the strong temporal dependencies inherent in humanoid locomotion, Mamba-2 is employed as the backbone of the Actor-Critic network, enabling efficient temporal modeling of historical observations and content-based reasoning with linear spatiotemporal complexity. Furthermore, to eliminate the tendency of humanoid robots to favor low-speed motion in order to maintain gait stability and balance, which often leads to inaccurate velocity command tracking, a command-guided curriculum learning (CGCL) method is proposed to improve responsiveness to velocity commands. Experimental results demonstrate that the proposed Mamba-based framework achieves state-of-the-art (SOTA) performance, while CGCL significantly enhances the accuracy of velocity command tracking. Moreover, sim-to-real transfer experiments confirm both the robustness and the seamless deployability of the proposed framework on physical humanoid platforms. Note to Practitioners—Humanoid robots offer superior adaptability and performance in human-centered, unstructured environments, but controlling their whole-body locomotion remains challenging. Most existing methods rely on model-based designs that require extensive manual tuning, limiting their flexibility. This work proposes a novel curriculum-enhanced reinforcement learning framework that improves robustness and generalization for humanoid locomotion. On one hand, the framework utilizes Mamba-2 as the backbone of the Actor-Critic architecture, improving computational efficiency compared with current Transformer-based methods while retaining the ability to reason over complex movement sequences. On the other hand, a command-guided curriculum learning (CGCL) method is proposed to enhance the ability of the robot to accurately track velocity commands. Experimental results demonstrate that the proposed method exhibits strong robustness and precise command-tracking capabilities, highlighting its significant potential for real-world applications in humanoid locomotion.

Förderung

  • National Natural Science Foundation of China
  • Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China

Zitieren

APA

Zhou, Y., Qiu, J., Jia, S., Ni, F., & Zhang, W. (2026). Curriculum-Enhanced Reinforcement Learning for Robust Humanoid Locomotion. IEEE Transactions on Automation Science and Engineering, 23, 5779-5789. https://doi.org/10.1109/tase.2026.3669985

Vancouver

Zhou Y, Qiu J, Jia S, Ni F, Zhang W. Curriculum-Enhanced Reinforcement Learning for Robust Humanoid Locomotion. IEEE Transactions on Automation Science and Engineering. 2026;23:5779-5789. doi:10.1109/tase.2026.3669985

BibTeX
@article{Zhou2026,
  author = {Zhou, Yi and Qiu, Jianbin and Jia, Shixiang and Ni, Fenglei and Zhang, Wei},
  title = {Curriculum-Enhanced Reinforcement Learning for Robust Humanoid Locomotion},
  journal = {IEEE Transactions on Automation Science and Engineering},
  year = {2026},
  volume = {23},
  pages = {5779--5789},
  doi = {10.1109/tase.2026.3669985}
}
Kostenlos starten →