Enhancing Tactile-based Reinforcement Learning for Robotic Control
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_ | 1866908610278195200 |
|---|---|
| author | Miller, Elle McInroe, Trevor Abel, David Mac Aodha, Oisin Vijayakumar, Sethu |
| author_facet | Miller, Elle McInroe, Trevor Abel, David Mac Aodha, Oisin Vijayakumar, Sethu |
| contents | Achieving safe, reliable real-world robotic manipulation requires agents to evolve beyond vision and incorporate tactile sensing to overcome sensory deficits and reliance on idealised state information. Despite its potential, the efficacy of tactile sensing in reinforcement learning (RL) remains inconsistent. We address this by developing self-supervised learning (SSL) methodologies to more effectively harness tactile observations, focusing on a scalable setup of proprioception and sparse binary contacts. We empirically demonstrate that sparse binary tactile signals are critical for dexterity, particularly for interactions that proprioceptive control errors do not register, such as decoupled robot-object motions. Our agents achieve superhuman dexterity in complex contact tasks (ball bouncing and Baoding ball rotation). Furthermore, we find that decoupling the SSL memory from the on-policy memory can improve performance. We release the Robot Tactile Olympiad (RoTO) benchmark to standardise and promote future research in tactile-based manipulation. Project page: https://elle-miller.github.io/tactile_rl |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21609 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Tactile-based Reinforcement Learning for Robotic Control Miller, Elle McInroe, Trevor Abel, David Mac Aodha, Oisin Vijayakumar, Sethu Robotics Machine Learning Achieving safe, reliable real-world robotic manipulation requires agents to evolve beyond vision and incorporate tactile sensing to overcome sensory deficits and reliance on idealised state information. Despite its potential, the efficacy of tactile sensing in reinforcement learning (RL) remains inconsistent. We address this by developing self-supervised learning (SSL) methodologies to more effectively harness tactile observations, focusing on a scalable setup of proprioception and sparse binary contacts. We empirically demonstrate that sparse binary tactile signals are critical for dexterity, particularly for interactions that proprioceptive control errors do not register, such as decoupled robot-object motions. Our agents achieve superhuman dexterity in complex contact tasks (ball bouncing and Baoding ball rotation). Furthermore, we find that decoupling the SSL memory from the on-policy memory can improve performance. We release the Robot Tactile Olympiad (RoTO) benchmark to standardise and promote future research in tactile-based manipulation. Project page: https://elle-miller.github.io/tactile_rl |
| title | Enhancing Tactile-based Reinforcement Learning for Robotic Control |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2510.21609 |