PhysiFlow: Physics-Aware Humanoid Whole-Body VLA via Multi-Brain Latent Flow Matching and Robust Tracking
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915837983588352 |
|---|---|
| author | Qin, Weikai Wu, Sichen Chen, Ci Liu, Mengfan Feng, Linxi Cui, Xinru Han, Haoqi Wang, Hesheng |
| author_facet | Qin, Weikai Wu, Sichen Chen, Ci Liu, Mengfan Feng, Linxi Cui, Xinru Han, Haoqi Wang, Hesheng |
| contents | In the domain of humanoid robot control, the fusion of Vision-Language-Action (VLA) with whole-body control is essential for semantically guided execution of real-world tasks. However, existing methods encounter challenges in terms of low VLA inference efficiency or an absence of effective semantic guidance for whole-body control, resulting in instability in dynamic limb-coordinated tasks. To bridge this gap, we present a semantic-motion intent guided, physics-aware multi-brain VLA framework for humanoid whole-body control. A series of experiments was conducted to evaluate the performance of the proposed framework. The experimental results demonstrated that the framework enabled reliable vision-language-guided full-body coordination for humanoid robots. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05410 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PhysiFlow: Physics-Aware Humanoid Whole-Body VLA via Multi-Brain Latent Flow Matching and Robust Tracking Qin, Weikai Wu, Sichen Chen, Ci Liu, Mengfan Feng, Linxi Cui, Xinru Han, Haoqi Wang, Hesheng Robotics In the domain of humanoid robot control, the fusion of Vision-Language-Action (VLA) with whole-body control is essential for semantically guided execution of real-world tasks. However, existing methods encounter challenges in terms of low VLA inference efficiency or an absence of effective semantic guidance for whole-body control, resulting in instability in dynamic limb-coordinated tasks. To bridge this gap, we present a semantic-motion intent guided, physics-aware multi-brain VLA framework for humanoid whole-body control. A series of experiments was conducted to evaluate the performance of the proposed framework. The experimental results demonstrated that the framework enabled reliable vision-language-guided full-body coordination for humanoid robots. |
| title | PhysiFlow: Physics-Aware Humanoid Whole-Body VLA via Multi-Brain Latent Flow Matching and Robust Tracking |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.05410 |