Learning In-Hand Translation Using Tactile Skin With Shear and Normal Force Sensing
This work addresses the challenge of adapting robotic manipulation to unseen object properties and orientations, representing an incremental improvement in tactile sensing for dexterous tasks.
The paper tackled the problem of dexterous in-hand translation by developing a tactile skin sensor model for zero-shot sim-to-real transfer of shear and normal forces, resulting in RL policies that consistently outperformed baselines using only shear forces, normal forces, or proprioception.
Recent progress in reinforcement learning (RL) and tactile sensing has significantly advanced dexterous manipulation. However, these methods often utilize simplified tactile signals due to the gap between tactile simulation and the real world. We introduce a sensor model for tactile skin that enables zero-shot sim-to-real transfer of ternary shear and binary normal forces. Using this model, we develop an RL policy that leverages sliding contact for dexterous in-hand translation. We conduct extensive real-world experiments to assess how tactile sensing facilitates policy adaptation to various unseen object properties and robot hand orientations. We demonstrate that our 3-axis tactile policies consistently outperform baselines that use only shear forces, only normal forces, or only proprioception. Website: https://jessicayin.github.io/tactile-skin-rl/