Abstract
Humanoid robots possess the structural capability to traverse complex terrains. However, achieving stable t raversal without relying on perceived information remains challenging, particularly in complex environments. This paper introduces DAMP, a reinforcement learning framework aimed at achieving robust and naturalistic humanoid locomotion over challenging terrains, with the assumption that no perceived information is available. The framework leverages recurrent neural networks to capture temporal dependencies and implicitly infer privileged and other task-relevant latent information. By aligning the learned representations with the task objective, the method enables robust and goal-consistent policy learning. This end-to-end framework achieves transfer learning from simulation to real-world environments, demonstrating the proposed method's robustness and generalization capabilities. The video of the real-world demonstration can be found at the following link: https://youtu.be/AkI7TZB2DDM.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Shen, P., Cui, W., Huang, H., Qin, B., Li, S., Dong, Z., & Zhang, G. (2026). DAMP: Humanoid Locomotion via Denoised Belief Learning and Adversarial Motion Priors. https://omanscience.com/en/articles/damp-humanoid-locomotion-via-denoised-belief-learning-and-adversarial-motion-priors
MLA 9
Shen, Puying, et al. "DAMP: Humanoid Locomotion via Denoised Belief Learning and Adversarial Motion Priors." https://omanscience.com/en/articles/damp-humanoid-locomotion-via-denoised-belief-learning-and-adversarial-motion-priors.
Chicago (author–date)
Shen, Puying, Wenhao Cui, Huaxing Huang, Bangyu Qin, Shengtao Li, Ziyang Dong, and Guoteng Zhang. 2026. "DAMP: Humanoid Locomotion via Denoised Belief Learning and Adversarial Motion Priors." https://omanscience.com/en/articles/damp-humanoid-locomotion-via-denoised-belief-learning-and-adversarial-motion-priors.
Harvard
Shen, P., Cui, W., Huang, H., Qin, B., Li, S., Dong, Z. and Zhang, G. (2026) 'DAMP: Humanoid Locomotion via Denoised Belief Learning and Adversarial Motion Priors', Available at: https://omanscience.com/en/articles/damp-humanoid-locomotion-via-denoised-belief-learning-and-adversarial-motion-priors.
Vancouver
Shen P, Cui W, Huang H, Qin B, Li S, Dong Z, et al. DAMP: Humanoid Locomotion via Denoised Belief Learning and Adversarial Motion Priors. https://omanscience.com/en/articles/damp-humanoid-locomotion-via-denoised-belief-learning-and-adversarial-motion-priors
IEEE
P. Shen, W. Cui, H. Huang, B. Qin, S. Li, Z. Dong, and G. Zhang, "DAMP: Humanoid Locomotion via Denoised Belief Learning and Adversarial Motion Priors," https://omanscience.com/en/articles/damp-humanoid-locomotion-via-denoised-belief-learning-and-adversarial-motion-priors.