الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Despite recent advances in humanoid locomotion, controllers optimized for command tracking and robustness tend to produce mechanical gaits, whereas controllers tied to human motion data often fail to generalize to commands outside the data distribution. This work introduces a learning framework that balances these competing objectives to synthesize real-time steerable, robust, and biomimetic locomotion policies from human data. Using an in-house curated locomotion dataset covering diverse speeds and directions, we first learn a natural locomotion prior policy through a teacher-student distillation process. Specifically, we train a full-body reference-conditioned policy with Reinforcement Learning (RL), then distill it into a lightweight prior policy conditioned solely on proprioception and a planar torso-velocity steering command. Next, we fine-tune the prior policy with multi-task RL to expand command coverage and robustness beyond the data distribution, pairing a goal-conditioned task that tracks arbitrary commands with a reference-guided task that tracks the human data as an explicit style regularizer. We validate our framework on three humanoid robots: the Boston Dynamics Atlas R1, Atlas D1, and Unitree G1. Experimental results demonstrate robust performance across real-world scenarios, including direct user-controlled locomotion in indoor and outdoor environments, and integration as the locomotion layer within hierarchical control stacks. Benchmarks against Tabula Rasa RL policies trained without human data and ablation studies confirm that our framework yields a lightweight, deployable policy that reconstructs coordinated whole-body behavior from a steering command, retaining the human gait characteristics while remaining robust and fully steerable.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Zhang, M., Kang, D., Bergamin, K., Burger, N., Deits, R., Foster, J., Hammoud, B., Hughes, K., Iacobelli, F., Koolen, T., Mungai, M. E., Nobles, Z., Rozen-Levy, S., Sleiman, J. P., Yu, F., Zhang, Y., Rizzi, A., Hodgins, J., Kuindersma, S., Abe, Y., Bertrand, S., & Farshidian, F. (2026). HuMBLE: تعلم السلوك المدفوع بحركة الإنسان للحركة المجسدة. https://omanscience.com/ar/articles/humble-human-motion-driven-behavior-learning-for-embodied-locomotion
MLA 9
Zhang, Mike, et al. "HuMBLE: تعلم السلوك المدفوع بحركة الإنسان للحركة المجسدة." https://omanscience.com/ar/articles/humble-human-motion-driven-behavior-learning-for-embodied-locomotion.
شيكاغو (المؤلف–التاريخ)
Zhang, Mike, Dongho Kang, Kevin Bergamin, Nicola Burger, Robin Deits, Jonathan Foster, Bilal Hammoud, Katie Hughes, Francesco Iacobelli, Twan Koolen, M. Eva Mungai, Zach Nobles, Shane Rozen-Levy, Jean Pierre Sleiman, Fangzhou Yu, Yunbo Zhang, Alfred Rizzi, Jessica Hodgins, Scott Kuindersma, Yeuhi Abe, Sylvain Bertrand, and Farbod Farshidian. 2026. "HuMBLE: تعلم السلوك المدفوع بحركة الإنسان للحركة المجسدة." https://omanscience.com/ar/articles/humble-human-motion-driven-behavior-learning-for-embodied-locomotion.
هارفارد
Zhang, M., Kang, D., Bergamin, K., Burger, N., Deits, R., Foster, J., Hammoud, B., Hughes, K., Iacobelli, F., Koolen, T., Mungai, M. E., Nobles, Z., Rozen-Levy, S., Sleiman, J. P., Yu, F., Zhang, Y., Rizzi, A., Hodgins, J., Kuindersma, S., Abe, Y., Bertrand, S. and Farshidian, F. (2026) 'HuMBLE: تعلم السلوك المدفوع بحركة الإنسان للحركة المجسدة', Available at: https://omanscience.com/ar/articles/humble-human-motion-driven-behavior-learning-for-embodied-locomotion.
فانكوفر
Zhang M, Kang D, Bergamin K, Burger N, Deits R, Foster J, et al. HuMBLE: تعلم السلوك المدفوع بحركة الإنسان للحركة المجسدة. https://omanscience.com/ar/articles/humble-human-motion-driven-behavior-learning-for-embodied-locomotion
IEEE
M. Zhang, D. Kang, K. Bergamin, N. Burger, R. Deits, J. Foster, B. Hammoud, K. Hughes, F. Iacobelli, T. Koolen, M. E. Mungai, Z. Nobles, S. Rozen-Levy, J. P. Sleiman, F. Yu, Y. Zhang, A. Rizzi, J. Hodgins, S. Kuindersma, Y. Abe, S. Bertrand, and F. Farshidian, "HuMBLE: تعلم السلوك المدفوع بحركة الإنسان للحركة المجسدة," https://omanscience.com/ar/articles/humble-human-motion-driven-behavior-learning-for-embodied-locomotion.