SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning
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_ | 1866911413195243520 |
|---|---|
| author | Pan, Xu Wan, Zhenglin Yu, Xingrui Zheng, Xianwei Ke, Youkai Sun, Ming Wang, Rui Wang, Ziwei Tsang, Ivor |
| author_facet | Pan, Xu Wan, Zhenglin Yu, Xingrui Zheng, Xianwei Ke, Youkai Sun, Ming Wang, Rui Wang, Ziwei Tsang, Ivor |
| contents | Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this degradation is closely associated with the erosion of spatial inductive bias during RL adaptation, as sparse rewards and spatially agnostic exploration increasingly favor short-horizon visual cues. To address this issue, we propose \textbf{SA-VLA}, a spatially-aware RL adaptation framework that preserves spatial grounding during policy optimization by aligning representation learning, reward design, and exploration with task geometry. SA-VLA fuses implicit spatial representations with visual tokens, provides dense rewards that reflect geometric progress, and employs \textbf{SCAN}, a spatially-conditioned annealed exploration strategy tailored to flow-matching dynamics. Across challenging multi-object and cluttered manipulation benchmarks, SA-VLA enables stable RL fine-tuning and improves zero-shot spatial generalization, yielding more robust and transferable behaviors. Code and project page are available at https://xupan.top/Projects/savla. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00743 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning Pan, Xu Wan, Zhenglin Yu, Xingrui Zheng, Xianwei Ke, Youkai Sun, Ming Wang, Rui Wang, Ziwei Tsang, Ivor Robotics Artificial Intelligence Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this degradation is closely associated with the erosion of spatial inductive bias during RL adaptation, as sparse rewards and spatially agnostic exploration increasingly favor short-horizon visual cues. To address this issue, we propose \textbf{SA-VLA}, a spatially-aware RL adaptation framework that preserves spatial grounding during policy optimization by aligning representation learning, reward design, and exploration with task geometry. SA-VLA fuses implicit spatial representations with visual tokens, provides dense rewards that reflect geometric progress, and employs \textbf{SCAN}, a spatially-conditioned annealed exploration strategy tailored to flow-matching dynamics. Across challenging multi-object and cluttered manipulation benchmarks, SA-VLA enables stable RL fine-tuning and improves zero-shot spatial generalization, yielding more robust and transferable behaviors. Code and project page are available at https://xupan.top/Projects/savla. |
| title | SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2602.00743 |