Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.27886 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917538253766656 |
|---|---|
| author | Wu, Qiwei Zhang, Rui Xiang, Xin Li, Tao Zhang, Weihua Lai, Junjie Xu, Renjing |
| author_facet | Wu, Qiwei Zhang, Rui Xiang, Xin Li, Tao Zhang, Weihua Lai, Junjie Xu, Renjing |
| contents | Tactile sensing is essential for robots to achieve human-like gentle manipulation. However, existing Vision-Language-Action (VLA) models struggle to exploit tactile feedback for gentle manipulation due to scarce aligned vision-tactile-language data and the lack of effective closed-loop force feedback mechanisms. To address these challenges, we introduce Tabero, a benchmark and model suite for gentle, language-conditioned robotic manipulation that demands fine-grained contact force perception. First, the Tabero benchmark addresses the scarcity of tactile data by presenting a data-efficient pipeline that repurposes open-source robot manipulation trajectories to generate diverse vision-tactile-language tasks, and establishes a multidimensional evaluation protocol that measures task success alongside physical interaction quality. Second, we propose Tabero-VTLA, an architecture with a decoupled force-position command interface; the resulting force-position commands are executed by a fixed hybrid controller to enable real-time, force-aware manipulation. Evaluated on Tabero, our model maintains high task success while reducing average grip force by over 70\% under gentle instructions, demonstrating its ability to modulate interaction forces based on multimodal experience. Our code is publicly available at https://github.com/NathanWu7/Tabero. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27886 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language Wu, Qiwei Zhang, Rui Xiang, Xin Li, Tao Zhang, Weihua Lai, Junjie Xu, Renjing Robotics Tactile sensing is essential for robots to achieve human-like gentle manipulation. However, existing Vision-Language-Action (VLA) models struggle to exploit tactile feedback for gentle manipulation due to scarce aligned vision-tactile-language data and the lack of effective closed-loop force feedback mechanisms. To address these challenges, we introduce Tabero, a benchmark and model suite for gentle, language-conditioned robotic manipulation that demands fine-grained contact force perception. First, the Tabero benchmark addresses the scarcity of tactile data by presenting a data-efficient pipeline that repurposes open-source robot manipulation trajectories to generate diverse vision-tactile-language tasks, and establishes a multidimensional evaluation protocol that measures task success alongside physical interaction quality. Second, we propose Tabero-VTLA, an architecture with a decoupled force-position command interface; the resulting force-position commands are executed by a fixed hybrid controller to enable real-time, force-aware manipulation. Evaluated on Tabero, our model maintains high task success while reducing average grip force by over 70\% under gentle instructions, demonstrating its ability to modulate interaction forces based on multimodal experience. Our code is publicly available at https://github.com/NathanWu7/Tabero. |
| title | Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language |
| topic | Robotics |
| url | https://arxiv.org/abs/2605.27886 |