用触觉反馈提升机器人抓握稳定性，实现高效精准的开盖操作
Tac2Motion: Contact-Aware Reinforcement Learning with Tactile Feedback for Robotic Hand Manipulation
- 基于触觉信号设计奖励函数并嵌入观测空间，增强抓握与指节协调
- 相比基线方法，数据效率更高，能在不同物体和摩擦条件下泛化
- 成功部署于真实多指机器人Shadow Robot，验证了实际应用可行性
本文提出Tac2Motion框架，通过触觉感知引导强化学习，实现高接触密度的抓握操作，如开盖任务。该框架将触觉信号融入观测空间并设计基于触觉的奖励机制，促使智能体同时实现稳固抓握与平滑指节运动。实验表明，该方法在开盖场景中具备更强的数据效率和鲁棒性，并可泛化至多种物体类型及扭转摩擦等动态变化。训练策略在真实多指机器人Shadow Robot上成功部署，验证了从仿真到现实的迁移能力。视频演示见：https://youtu.be/poeJBPR7urQ。
原文摘要 · Abstract (English)
This paper proposes Tac2Motion, a contact-aware reinforcement learning framework to facilitate the learning of contact-rich in-hand manipulation tasks, such as removing a lid. To this end, we propose tactile sensing-based reward shaping and incorporate the sensing into the observation space through embedding. The designed rewards encourage an agent to ensure firm grasping and smooth finger gaiting at the same time, leading to higher data efficiency and robust performance compared to the baseline. We verify the proposed framework on the opening a lid scenario, showing generalization of the trained policy into a couple of object types and various dynamics such as torsional friction. Lastly, the learned policy is demonstrated on the multi-fingered robot, Shadow Robot, showing that the control policy can be transferred to the real world. The video is available: https://youtu.be/poeJBPR7urQ.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。