PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking
Jiacheng Bao, Haoran Yang, Yucheng Xin, Junhong Liu, Yuecheng Xu, Han Liang, Pengfei Han, Xiaoguang Ma, Dong Wang, Bin Zhao

TL;DR
PhyGile introduces a physics-guided motion generation framework for humanoid robots, enabling agile, stable, and realistic whole-body motions directly from text prompts, surpassing prior methods in complexity and stability.
Contribution
It presents a novel physics-prefix-guided motion generation method that directly produces robot-native motions, reducing artifacts and improving execution fidelity in humanoid control.
Findings
Enables stable tracking of complex, agile motions on real robots.
Reduces inference-time retargeting artifacts and discrepancies.
Outperforms prior methods in executing difficult motions.
Abstract
Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation models are predominantly trained on captured human motion datasets, whose priors assume human biomechanics, actuation, mass distribution, and contact strategies. When such motions are directly retargeted to humanoid robots, the resulting trajectories may satisfy geometric constraints (e.g., joint limits and pose continuity) and appear kinematically reasonable. However, they frequently violate the physical feasibility required for real-world execution. To address these issues, we present PhyGile, a unified framework that closes the loop between robot-native motion generation and General Motion Tracking (GMT). PhyGile performs physics-prefix-guided robot-native motion generation at inference time, directly generating robot-native motions in a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Motion and Animation · Robotic Locomotion and Control · Robot Manipulation and Learning
