具身智能观察

PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking

技术动态

来源:arXiv cs.RO发布时间待核实

arXiv:2603.19305v3 Announce Type: replace 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.