InsertAnything：从仿真到现实的泛化性高接触精度插入
InsertAnything: Generalizable Contact-Rich Precision Insertion from Simulation to Reality
- University of Chinese Academy of Sciences（中国科学院大学）
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- PaXini AI Technology (Beijing) Co., Ltd.（北京他山科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
提出一种完全在仿真中训练的强化学习框架，结合目标位姿和指尖力反馈，实现无需真实演示即可直接部署的高精度插入策略，在ManipulationNet基准上首次获得满分，并在跨任务中达到95%成功率。
中文摘要 AI 辅助
高接触精度插入是机器人装配中的一项关键操作技能。紧密的间隙使插入对对齐误差更加敏感，容易发生碰撞和卡阻，而零件之间几何形状和间隙的变化进一步增加了策略复用的复杂性。我们提出了一种强化学习框架，该框架完全在仿真中训练插入策略，无需真实世界演示或策略微调即可直接部署。通过将目标位姿与紧凑的三维指尖力反馈相结合，策略学会在估计孔位存在误差的情况下搜索对齐并纠正其运动。一个解耦的门控奖励协调对齐和插入过程。力信号平滑和状态无关的标准差稳定了学习过程。所得策略在多种孔几何形状下执行真实世界插入，最小标称间隙为0.02毫米，并在孔位误差下提高成功率同时降低峰值接触力。跨间隙和跨几何形状的评估进一步证实了策略的泛化性。该系统在ManipulationNet的插销入孔基准测试中，在其人机交互协议下首次获得满分20/20，且插入运动完全自主。仅在一个模拟六边形插入任务上训练的策略，在八个未见过的真实世界插入任务中实现了95.0%的总体成功率。这些结果表明，完全在仿真中学习可以产生能够直接部署并跨真实世界任务复用的精度插入技能。项目网站（此HTTPS URL）提供了开源的仿真和真实机器人实验脚本、资产以及训练好的检查点。
英文摘要
Contact-rich precision insertion is a key manipulation skill in robotic assembly. Tight clearances make insertion more sensitive to alignment errors and prone to collisions and jamming, while variations in geometry and clearance across parts further complicate policy reuse. We present a reinforcement learning framework that trains insertion policies entirely in simulation for direct deployment without real-world demonstrations or policy fine-tuning. By combining target poses with compact three-dimensional fingertip force feedback, the policy learns to search for alignment and correct its motion despite errors in the estimated hole position. A decoupled gated reward coordinates alignment and insertion. Force-signal smoothing and state-independent standard deviations stabilize the learning process. The resulting policies perform real-world insertion across multiple hole geometries with a minimum nominal clearance of 0.02 mm and improve success while reducing peak contact forces under hole-position errors. Cross-clearance and cross-geometry evaluations further confirm policy generalization. The system achieved the first perfect score of 20/20 on ManipulationNet's peg-in-hole benchmark under its Human-in-the-Loop protocol, with fully autonomous insertion motions. A single policy trained only on a simulated hexagonal insertion task achieved an overall success rate of 95.0% across eight unseen real-world insertion tasks. These results show that learning entirely in simulation can yield precision insertion skills that can be deployed directly and reused across real-world tasks. The project website (https://mzhsoul.github.io/InsertAnything/) provides open-source simulation and real-robot experiment scripts, assets, and trained checkpoints.
