Enhancing Tactile-based Reinforcement Learning for Robotic Control

2025-10-24 · Elle Miller, Trevor McInroe, David Abel, Oisin Mac Aodha, Sethu Vijayakumar arxiv

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

📄 PDF Abstract BibTeX arXiv:2510.21609

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning Reinforcement Learning

TIAGo RL: Simulated Reinforcement Learning Environments with Tactile Data for Mobile Robots

2023-11-13 · Luca Lach, Francesco Ferro, Robert Haschke

Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling beh…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Transfer Learning

Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation

2021-06-16 · Alex Church, John Lloyd, Raia Hadsell, Nathan F. Lepora

Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually consider…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

The Role of Tactile Sensing in Learning and Deploying Grasp Refinement Algorithms

2021-09-23 · Alexander Koenig, Zixi Liu, Lucas Janson, Robert Howe

A long-standing question in robot hand design is how accurate tactile sensing must be. This paper uses simulated tactile signals and the reinforcement learning (RL) framework to study the sensing needs in grasping system…

Reinforcement Learning (RL)Robotic Grasping

ViTacGen: Robotic Pushing with Vision-to-Touch Generation

2025-10-15 · Zhiyuan Wu, Yijiong Lin, Yongqiang Zhao, Xuyang Zhang 외 arxiv

Robotic pushing is a fundamental manipulation task that requires tactile feedback to capture subtle contact forces and dynamics between the end-effector and the object. However, real tactile sensors often face hardware l…

Reinforcement Learning Contrastive Learning Robot Manipulation

Tactile Active Inference Reinforcement Learning for Efficient Robotic Manipulation Skill Acquisition

2023-11-19 · Zihao Liu, Xing Liu, Yizhai Zhang, Zhengxiong Liu 외

Robotic manipulation holds the potential to replace humans in the execution of tedious or dangerous tasks. However, control-based approaches are not suitable due to the difficulty of formally describing open-world manipu…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)