ReViP: Mitigating False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910050171224064 |
|---|---|
| author | Li, Zhuohao Li, Yinghao Jiang, Jian-Jian Zhou, Lang Zhang, Tianyu Yin, Jiadong Lin, Mu Wei, Yi-Lin Zheng, Wei-Shi |
| author_facet | Li, Zhuohao Li, Yinghao Jiang, Jian-Jian Zhou, Lang Zhang, Tianyu Yin, Jiadong Lin, Mu Wei, Yi-Lin Zheng, Wei-Shi |
| contents | Vision-Language-Action (VLA) models have advanced robotic manipulation by combining vision, language, and proprioception to predict actions. However, previous methods fuse proprioceptive signals directly with vision-language features, resulting in state-dominant bias and \textbf{false completions} despite visible execution failures. We systematically analyze this failure mode, attributing it to modality imbalance, where policies overly rely on internal state progression and underuse visual evidence. To address this, we introduce the first \textbf{False-Completion Benchmark Suite}, featuring eight tasks with three controlled perturbations (\emph{Object Drop}, \emph{Distractor Swap}, \emph{Relayout}) to comprehensively evaluate false completion. Moreover, we propose \textbf{ReViP}, a novel VLA framework with \textbf{Vi}sion-\textbf{P}roprioception \textbf{Re}balance to enhance visual grounding and robustness under perturbations. The key insight is to introduce auxiliary \emph{progress-aware visual cues} to adaptively modulate the coupling between semantic perception and proprioceptive dynamics. Specifically, progress-aware visual cues are extracted by an external Task-Stage Observer, which performs task-relevant reasoning on real-time observations to drive task-stage feature-wise linear modulation, enhancing environmental awareness and mitigating state-driven errors. Extensive experiments show that ReViP effectively mitigates false completion and improves success rates over strong VLA baselines, achieving a \textbf{26\%} gain over $π_0$ model on our suite, with gains extending to LIBERO, RoboTwin 2.0, and real-world evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16667 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ReViP: Mitigating False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance Li, Zhuohao Li, Yinghao Jiang, Jian-Jian Zhou, Lang Zhang, Tianyu Yin, Jiadong Lin, Mu Wei, Yi-Lin Zheng, Wei-Shi Robotics Computer Vision and Pattern Recognition Vision-Language-Action (VLA) models have advanced robotic manipulation by combining vision, language, and proprioception to predict actions. However, previous methods fuse proprioceptive signals directly with vision-language features, resulting in state-dominant bias and \textbf{false completions} despite visible execution failures. We systematically analyze this failure mode, attributing it to modality imbalance, where policies overly rely on internal state progression and underuse visual evidence. To address this, we introduce the first \textbf{False-Completion Benchmark Suite}, featuring eight tasks with three controlled perturbations (\emph{Object Drop}, \emph{Distractor Swap}, \emph{Relayout}) to comprehensively evaluate false completion. Moreover, we propose \textbf{ReViP}, a novel VLA framework with \textbf{Vi}sion-\textbf{P}roprioception \textbf{Re}balance to enhance visual grounding and robustness under perturbations. The key insight is to introduce auxiliary \emph{progress-aware visual cues} to adaptively modulate the coupling between semantic perception and proprioceptive dynamics. Specifically, progress-aware visual cues are extracted by an external Task-Stage Observer, which performs task-relevant reasoning on real-time observations to drive task-stage feature-wise linear modulation, enhancing environmental awareness and mitigating state-driven errors. Extensive experiments show that ReViP effectively mitigates false completion and improves success rates over strong VLA baselines, achieving a \textbf{26\%} gain over $π_0$ model on our suite, with gains extending to LIBERO, RoboTwin 2.0, and real-world evaluations. |
| title | ReViP: Mitigating False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.16667 |