从不完美的仿真中学习灵巧操作技能
Learning Dexterous Manipulation Skills from Imperfect Simulations
AI总结：
本研究提出\ours框架，通过仿真到现实迁移解决复杂接触动力学和触觉反馈问题，实现多指手在螺母拧紧和螺丝驱动任务中的高效操作。
摘要：
强化学习和仿真到现实的迁移在灵巧操作方面取得了显著进展。然而，进展仍受到复杂接触动力学和多感官信号模拟的难度限制，尤其是触觉反馈。在本工作中，我们提出了\ours，一个仿真到现实的框架，旨在解决这些限制，并在多指手的螺母拧紧和螺丝驱动任务中展示了其有效性。该框架有三个阶段。首先，我们使用简化的物体模型在仿真中训练强化学习策略，从而产生正确的手指运动模式。然后，我们使用所学的策略作为 teleoperation 系统中的技能原语来收集现实世界中的演示，这些演示包含触觉和本体感觉信息。最后，我们训练了一个行为克隆策略，该策略结合了触觉传感，并显示其能够推广到具有不同几何形状的螺母和螺丝刀。在两个任务上的实验显示，与直接的仿真到现实迁移相比，任务进度比值较高，并且在未见过的对象形状和外部扰动下表现出鲁棒性。视频和代码可在 https://dexscrew.github.io 上获得。
英文摘要：
Reinforcement learning and sim-to-real transfer have made significant progress in dexterous manipulation. However, progress remains limited by the difficulty of simulating complex contact dynamics and multisensory signals, especially tactile feedback. In this work, we propose \ours, a sim-to-real framework that addresses these limitations and demonstrates its effectiveness on nut-bolt fastening and screwdriving with multi-fingered hands. The framework has three stages. First, we train reinforcement learning policies in simulation using simplified object models that lead to the emergence of correct finger gaits. We then use the learned policy as a skill primitive within a teleoperation system to collect real-world demonstrations that contain tactile and proprioceptive information. Finally, we train a behavior cloning policy that incorporates tactile sensing and show that it generalizes to nuts and screwdrivers with diverse geometries. Experiments across both tasks show high task progress ratios compared to direct sim-to-real transfer and robust performance even on unseen object shapes and under external perturbations. Videos and code are available on https://dexscrew.github.io.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
