Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.10093 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917264823943168 |
|---|---|
| author | Chen, Baijun Wan, Weijie Chen, Tianxing Guo, Xianda Xu, Congsheng Qi, Yuanyang Zhang, Haojie Wu, Longyan Xu, Tianling Li, Zixuan Wu, Yizhe Li, Rui Yang, Xiaokang Luo, Ping Sui, Wei Mu, Yao |
| author_facet | Chen, Baijun Wan, Weijie Chen, Tianxing Guo, Xianda Xu, Congsheng Qi, Yuanyang Zhang, Haojie Wu, Longyan Xu, Tianling Li, Zixuan Wu, Yizhe Li, Rui Yang, Xiaokang Luo, Ping Sui, Wei Mu, Yao |
| contents | Robotic manipulation has seen rapid progress with vision-language-action (VLA) policies. However, visuo-tactile perception is critical for contact-rich manipulation, as tasks such as insertion are difficult to complete robustly using vision alone. At the same time, acquiring large-scale and reliable tactile data in the physical world remains costly and challenging, and the lack of a unified evaluation platform further limits policy learning and systematic analysis. To address these challenges, we propose UniVTAC, a simulation-based visuo-tactile data synthesis platform that supports three commonly used visuo-tactile sensors and enables scalable and controllable generation of informative contact interactions. Based on this platform, we introduce the UniVTAC Encoder, a visuo-tactile encoder trained on large-scale simulation-synthesized data with designed supervisory signals, providing tactile-centric visuo-tactile representations for downstream manipulation tasks. In addition, we present the UniVTAC Benchmark, which consists of eight representative visuo-tactile manipulation tasks for evaluating tactile-driven policies. Experimental results show that integrating the UniVTAC Encoder improves average success rates by 17.1% on the UniVTAC Benchmark, while real-world robotic experiments further demonstrate a 25% improvement in task success. Our webpage is available at https://univtac.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10093 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarking Chen, Baijun Wan, Weijie Chen, Tianxing Guo, Xianda Xu, Congsheng Qi, Yuanyang Zhang, Haojie Wu, Longyan Xu, Tianling Li, Zixuan Wu, Yizhe Li, Rui Yang, Xiaokang Luo, Ping Sui, Wei Mu, Yao Robotics Robotic manipulation has seen rapid progress with vision-language-action (VLA) policies. However, visuo-tactile perception is critical for contact-rich manipulation, as tasks such as insertion are difficult to complete robustly using vision alone. At the same time, acquiring large-scale and reliable tactile data in the physical world remains costly and challenging, and the lack of a unified evaluation platform further limits policy learning and systematic analysis. To address these challenges, we propose UniVTAC, a simulation-based visuo-tactile data synthesis platform that supports three commonly used visuo-tactile sensors and enables scalable and controllable generation of informative contact interactions. Based on this platform, we introduce the UniVTAC Encoder, a visuo-tactile encoder trained on large-scale simulation-synthesized data with designed supervisory signals, providing tactile-centric visuo-tactile representations for downstream manipulation tasks. In addition, we present the UniVTAC Benchmark, which consists of eight representative visuo-tactile manipulation tasks for evaluating tactile-driven policies. Experimental results show that integrating the UniVTAC Encoder improves average success rates by 17.1% on the UniVTAC Benchmark, while real-world robotic experiments further demonstrate a 25% improvement in task success. Our webpage is available at https://univtac.github.io/. |
| title | UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarking |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.10093 |