Tactile information plays a critical role in human dexterity. It reveals useful contact information that may not be inferred directly from vision. In fact, humans can even perform in-hand dexterous manipulation without using vision. Can we enable the same ability for the multi-finger robot hand? In this paper, we present Touch Dexterity, a new system that can perform in-hand object rotation using only touching without seeing the object. Instead of relying on precise tactile sensing in a small region, we introduce a new system design using dense binary force sensors (touch or no touch) overlaying one side of the whole robot hand (palm, finger links, fingertips). Such a design is low-cost, giving a larger coverage of the object, and minimizing the Sim2Real gap at the same time. We train an in-hand rotation policy using Reinforcement Learning on diverse objects in simulation. Relying on touch-only sensing, we can directly deploy the policy in a real robot hand and rotate novel objects that are not presented in training. Extensive ablations are performed on how tactile information help in-hand manipulation.Our project is available at https://touchdexterity.github.io.

翻译：触觉信息在人类手部灵巧性中起着关键作用。它揭示了视觉可能无法直接推断出的有用接触信息。事实上，人类甚至可以在不使用视觉的情况下进行手部灵巧操作。我们能否让多指机械手也具备同样的能力？本文介绍了Touch Dexterity系统，该系统仅依靠触觉（不观察物体）即可实现手部物体旋转。我们并非依赖小区域内的精确触觉传感，而是提出了一种新的系统设计，在整只机械手的一侧（手掌、指节、指尖）覆盖密集的二进制力传感器（接触或未接触）。这种设计成本低廉，能提供更大的物体覆盖范围，同时缩小了模拟到现实（Sim2Real）的差距。我们通过强化学习在模拟环境中对多种物体训练了手部旋转策略。仅依靠触觉感知，该策略可直接部署到真实机械手上，并旋转训练中未曾见过的新物体。我们通过大量消融实验分析了触觉信息对手部灵巧操作的帮助。我们的项目页面见https://touchdexterity.github.io。