FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulation
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_ | 1866914356017496064 |
|---|---|
| author | Li, Yao Tang, Peiyuan Zhang, Wuyang Zhu, Chengyang Duan, Yifan Shi, Weikai Zhang, Xiaodong Yang, Zijiang Ji, Jianmin Zhang, Yanyong |
| author_facet | Li, Yao Tang, Peiyuan Zhang, Wuyang Zhu, Chengyang Duan, Yifan Shi, Weikai Zhang, Xiaodong Yang, Zijiang Ji, Jianmin Zhang, Yanyong |
| contents | Force/torque feedback can substantially improve Vision-Language-Action (VLA) models on contact-rich manipulation, but most existing approaches fuse all modalities at a single operating frequency. This design ignores the mismatched sampling rates of real robot sensors, forcing downsampling of the high-frequency contact cues needed for reactive correction. Combined with common VLM-action-expert (AE) pipelines that execute action chunks largely open loop between expensive VLM updates, unified-frequency fusion often yields delayed responses to impacts, stick-slip, and force spikes. We propose FAVLA, a force-adaptive fast-slow VLA that decouples slow perception planning from fast contact-aware control. FAVLA runs a slow VLM at a fixed low frequency to encode modalities to produce latent representations and to predict near-future force variation. A fast AE then executes at a variable high frequency, conditioning on the latest force sequence data to generate reactive actions. We further introduce a force adapter that injects high-frequency force features into multiple AE layers, and adaptively schedules the AE's execution frequency based on the VLM's predicted force variation. Extensive experiments on contact-rich tasks demonstrate that FAVLA significantly outperforms baselines, achieving superior reactivity and success rates, especially with a smaller contact force during manipulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23648 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulation Li, Yao Tang, Peiyuan Zhang, Wuyang Zhu, Chengyang Duan, Yifan Shi, Weikai Zhang, Xiaodong Yang, Zijiang Ji, Jianmin Zhang, Yanyong Robotics Force/torque feedback can substantially improve Vision-Language-Action (VLA) models on contact-rich manipulation, but most existing approaches fuse all modalities at a single operating frequency. This design ignores the mismatched sampling rates of real robot sensors, forcing downsampling of the high-frequency contact cues needed for reactive correction. Combined with common VLM-action-expert (AE) pipelines that execute action chunks largely open loop between expensive VLM updates, unified-frequency fusion often yields delayed responses to impacts, stick-slip, and force spikes. We propose FAVLA, a force-adaptive fast-slow VLA that decouples slow perception planning from fast contact-aware control. FAVLA runs a slow VLM at a fixed low frequency to encode modalities to produce latent representations and to predict near-future force variation. A fast AE then executes at a variable high frequency, conditioning on the latest force sequence data to generate reactive actions. We further introduce a force adapter that injects high-frequency force features into multiple AE layers, and adaptively schedules the AE's execution frequency based on the VLM's predicted force variation. Extensive experiments on contact-rich tasks demonstrate that FAVLA significantly outperforms baselines, achieving superior reactivity and success rates, especially with a smaller contact force during manipulation. |
| title | FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.23648 |