Tac2Motion: Contact-Aware Reinforcement Learning with Tactile Feedback for Robotic Hand Manipulation
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_ | 1866911272931426304 |
|---|---|
| author | Kim, Yitaek Rask, Casper Hewson Sloth, Christoffer |
| author_facet | Kim, Yitaek Rask, Casper Hewson Sloth, Christoffer |
| contents | This paper proposes Tac2Motion, a contact-aware reinforcement learning framework to facilitate the learning of contact-rich in-hand manipulation tasks, such as removing a lid. To this end, we propose tactile sensing-based reward shaping and incorporate the sensing into the observation space through embedding. The designed rewards encourage an agent to ensure firm grasping and smooth finger gaiting at the same time, leading to higher data efficiency and robust performance compared to the baseline. We verify the proposed framework on the opening a lid scenario, showing generalization of the trained policy into a couple of object types and various dynamics such as torsional friction. Lastly, the learned policy is demonstrated on the multi-fingered robot, Shadow Robot, showing that the control policy can be transferred to the real world. The video is available: https://youtu.be/poeJBPR7urQ. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17812 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tac2Motion: Contact-Aware Reinforcement Learning with Tactile Feedback for Robotic Hand Manipulation Kim, Yitaek Rask, Casper Hewson Sloth, Christoffer Robotics This paper proposes Tac2Motion, a contact-aware reinforcement learning framework to facilitate the learning of contact-rich in-hand manipulation tasks, such as removing a lid. To this end, we propose tactile sensing-based reward shaping and incorporate the sensing into the observation space through embedding. The designed rewards encourage an agent to ensure firm grasping and smooth finger gaiting at the same time, leading to higher data efficiency and robust performance compared to the baseline. We verify the proposed framework on the opening a lid scenario, showing generalization of the trained policy into a couple of object types and various dynamics such as torsional friction. Lastly, the learned policy is demonstrated on the multi-fingered robot, Shadow Robot, showing that the control policy can be transferred to the real world. The video is available: https://youtu.be/poeJBPR7urQ. |
| title | Tac2Motion: Contact-Aware Reinforcement Learning with Tactile Feedback for Robotic Hand Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.17812 |