TacLoc: Global Tactile Localization on Objects from a Registration Perspective
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910049149911040 |
|---|---|
| author | Zhang, Zirui Zhang, Boyang Zhang, Fumin Yin, Huan |
| author_facet | Zhang, Zirui Zhang, Boyang Zhang, Fumin Yin, Huan |
| contents | Pose estimation is essential for robotic manipulation, particularly when visual perception is occluded during gripper-object interactions. Existing tactile-based methods generally rely on tactile simulation or pre-trained models, which limits their generalizability and efficiency. In this study, we propose TacLoc, a novel tactile localization framework that formulates the problem as a one-shot point cloud registration task. TacLoc introduces a graph-theoretic partial-to-full registration method, leveraging dense point clouds and surface normals from tactile sensing for efficient and accurate pose estimation. Without requiring rendered data or pre-trained models, TacLoc achieves improved performance through normal-guided graph pruning and a hypothesis-and-verification pipeline. TacLoc is evaluated extensively on the YCB dataset. We further demonstrate TacLoc on real-world objects across two different visual-tactile sensors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10565 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TacLoc: Global Tactile Localization on Objects from a Registration Perspective Zhang, Zirui Zhang, Boyang Zhang, Fumin Yin, Huan Robotics Pose estimation is essential for robotic manipulation, particularly when visual perception is occluded during gripper-object interactions. Existing tactile-based methods generally rely on tactile simulation or pre-trained models, which limits their generalizability and efficiency. In this study, we propose TacLoc, a novel tactile localization framework that formulates the problem as a one-shot point cloud registration task. TacLoc introduces a graph-theoretic partial-to-full registration method, leveraging dense point clouds and surface normals from tactile sensing for efficient and accurate pose estimation. Without requiring rendered data or pre-trained models, TacLoc achieves improved performance through normal-guided graph pruning and a hypothesis-and-verification pipeline. TacLoc is evaluated extensively on the YCB dataset. We further demonstrate TacLoc on real-world objects across two different visual-tactile sensors. |
| title | TacLoc: Global Tactile Localization on Objects from a Registration Perspective |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.10565 |