OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908906576412672 |
|---|---|
| author | Zheng, Yuhang Gu, Songen Li, Weize Zheng, Yupeng Zang, Yujie Tian, Shuai Li, Xiang Hao, Ce Gao, Chen Liu, Si Li, Haoran Chen, Yilun Yan, Shuicheng Ding, Wenchao |
| author_facet | Zheng, Yuhang Gu, Songen Li, Weize Zheng, Yupeng Zang, Yujie Tian, Shuai Li, Xiang Hao, Ce Gao, Chen Liu, Si Li, Haoran Chen, Yilun Yan, Shuicheng Ding, Wenchao |
| contents | Contact-rich manipulation tasks, such as wiping and assembly, require accurate perception of contact forces, friction changes, and state transitions that cannot be reliably inferred from vision alone. Despite growing interest in visuo-tactile manipulation, progress is constrained by two persistent limitations: existing datasets are small in scale and narrow in task coverage, and current methods treat tactile signals as passive observations rather than using them to model contact dynamics or enable closed-loop control explicitly. In this paper, we present \textbf{OmniViTac}, a large-scale visuo-tactile-action dataset comprising $21{,}000+$ trajectories across $86$ tasks and $100+$ objects, organized into six physics-grounded interaction patterns. Building on this dataset, we propose \textbf{OmniVTA}, a world-model-based visuo-tactile manipulation framework that integrates four tightly coupled modules: a self-supervised tactile encoder, a two-stream visuo-tactile world model for predicting short-horizon contact evolution, a contact-aware fusion policy for action generation, and a 60Hz reflexive controller that corrects deviations between predicted and observed tactile signals in a closed loop. Real-robot experiments across all six interaction categories show that OmniVTA outperforms existing methods and generalizes well to unseen objects and geometric configurations, confirming the value of combining predictive contact modeling with high-frequency tactile feedback for contact-rich manipulation. All data, models, and code will be made publicly available on the project website at https://mrsecant.github.io/OmniVTA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19201 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation Zheng, Yuhang Gu, Songen Li, Weize Zheng, Yupeng Zang, Yujie Tian, Shuai Li, Xiang Hao, Ce Gao, Chen Liu, Si Li, Haoran Chen, Yilun Yan, Shuicheng Ding, Wenchao Robotics Contact-rich manipulation tasks, such as wiping and assembly, require accurate perception of contact forces, friction changes, and state transitions that cannot be reliably inferred from vision alone. Despite growing interest in visuo-tactile manipulation, progress is constrained by two persistent limitations: existing datasets are small in scale and narrow in task coverage, and current methods treat tactile signals as passive observations rather than using them to model contact dynamics or enable closed-loop control explicitly. In this paper, we present \textbf{OmniViTac}, a large-scale visuo-tactile-action dataset comprising $21{,}000+$ trajectories across $86$ tasks and $100+$ objects, organized into six physics-grounded interaction patterns. Building on this dataset, we propose \textbf{OmniVTA}, a world-model-based visuo-tactile manipulation framework that integrates four tightly coupled modules: a self-supervised tactile encoder, a two-stream visuo-tactile world model for predicting short-horizon contact evolution, a contact-aware fusion policy for action generation, and a 60Hz reflexive controller that corrects deviations between predicted and observed tactile signals in a closed loop. Real-robot experiments across all six interaction categories show that OmniVTA outperforms existing methods and generalizes well to unseen objects and geometric configurations, confirming the value of combining predictive contact modeling with high-frequency tactile feedback for contact-rich manipulation. All data, models, and code will be made publicly available on the project website at https://mrsecant.github.io/OmniVTA. |
| title | OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.19201 |