Enhancing Tactile-based Reinforcement Learning for Robotic Control
This work addresses the problem of improving robotic manipulation safety and reliability for real-world applications by enhancing tactile-based reinforcement learning, though it appears incremental as it builds on existing self-supervised and tactile sensing approaches.
The paper tackled the inconsistent efficacy of tactile sensing in reinforcement learning for robotic manipulation by developing self-supervised learning methods to better utilize sparse binary tactile signals, resulting in superhuman dexterity in tasks like ball bouncing and Baoding ball rotation.
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