{"ID":2868410,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16638","arxiv_id":"2509.16638","title":"KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control","abstract":"Learning versatile whole-body skills by tracking various human motions is a fundamental step toward general-purpose humanoid robots. This task is particularly challenging because a single policy must master a broad repertoire of motion skills while ensuring stability over long-horizon sequences. To this end, we present VMS, a unified whole-body controller that enables humanoid robots to learn diverse and dynamic behaviors within a single policy. Our framework integrates a hybrid tracking objective that balances local motion fidelity with global trajectory consistency, and an Orthogonal Mixture-of-Experts (OMoE) architecture that encourages skill specialization while enhancing generalization across motions. A segment-level tracking reward is further introduced to relax rigid step-wise matching, enhancing robustness when handling global displacements and transient inaccuracies. We validate VMS extensively in both simulation and real-world experiments, demonstrating accurate imitation of dynamic skills, stable performance over minute-long sequences, and strong generalization to unseen motions. These results highlight the potential of VMS as a scalable foundation for versatile humanoid whole-body control. The project page is available at https://kungfubot2-humanoid.github.io.","short_abstract":"Learning versatile whole-body skills by tracking various human motions is a fundamental step toward general-purpose humanoid robots. This task is particularly challenging because a single policy must master a broad repertoire of motion skills while ensuring stability over long-horizon sequences. To this end, we present...","url_abs":"https://arxiv.org/abs/2509.16638","url_pdf":"https://arxiv.org/pdf/2509.16638v1","authors":"[\"Jinrui Han\",\"Weiji Xie\",\"Jiakun Zheng\",\"Jiyuan Shi\",\"Weinan Zhang\",\"Ting Xiao\",\"Chenjia Bai\"]","published":"2025-09-20T11:31:14Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[]","has_code":false}