Object Pose Estimation through Dexterous Touch
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915497932488704 |
|---|---|
| author | Shahidzadeh, Amir-Hossein Zhu, Jiyue Chen, Kezhou Yi, Sha Fermüller, Cornelia Aloimonos, Yiannis Wang, Xiaolong |
| author_facet | Shahidzadeh, Amir-Hossein Zhu, Jiyue Chen, Kezhou Yi, Sha Fermüller, Cornelia Aloimonos, Yiannis Wang, Xiaolong |
| contents | Robust object pose estimation is essential for manipulation and interaction tasks in robotics, particularly in scenarios where visual data is limited or sensitive to lighting, occlusions, and appearances. Tactile sensors often offer limited and local contact information, making it challenging to reconstruct the pose from partial data. Our approach uses sensorimotor exploration to actively control a robot hand to interact with the object. We train with Reinforcement Learning (RL) to explore and collect tactile data. The collected 3D point clouds are used to iteratively refine the object's shape and pose. In our setup, one hand holds the object steady while the other performs active exploration. We show that our method can actively explore an object's surface to identify critical pose features without prior knowledge of the object's geometry. Supplementary material and more demonstrations will be provided at https://amirshahid.github.io/BimanualTactilePose . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13591 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Object Pose Estimation through Dexterous Touch Shahidzadeh, Amir-Hossein Zhu, Jiyue Chen, Kezhou Yi, Sha Fermüller, Cornelia Aloimonos, Yiannis Wang, Xiaolong Robotics Computer Vision and Pattern Recognition Robust object pose estimation is essential for manipulation and interaction tasks in robotics, particularly in scenarios where visual data is limited or sensitive to lighting, occlusions, and appearances. Tactile sensors often offer limited and local contact information, making it challenging to reconstruct the pose from partial data. Our approach uses sensorimotor exploration to actively control a robot hand to interact with the object. We train with Reinforcement Learning (RL) to explore and collect tactile data. The collected 3D point clouds are used to iteratively refine the object's shape and pose. In our setup, one hand holds the object steady while the other performs active exploration. We show that our method can actively explore an object's surface to identify critical pose features without prior knowledge of the object's geometry. Supplementary material and more demonstrations will be provided at https://amirshahid.github.io/BimanualTactilePose . |
| title | Object Pose Estimation through Dexterous Touch |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.13591 |