发表机构
Amazon; Duke University; University of Maryland, College Park; The University of Texas at Austin; University of Michigan（亚马逊; 杜克大学; 马里兰大学帕克分校; 德克萨斯大学奥斯汀分校; 密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ReDex通过手指级柔顺交互修正接触失败并引入力反馈，将仿真训练的灵巧策略迁移到现实，显著提升接触密集任务的成功率。
AI 中文摘要
在仿真中训练的灵巧操作策略常因接触时序和力调节误差而无法迁移到现实世界。然而，这些策略仍保留了可用于任务推进的多指协调能力。我们提出ReDex，一个通过修正局部接触失败并整合触觉反馈来使仿真训练的基础策略适应现实世界的框架。从仅基于本体感觉的基础策略出发，ReDex允许操作员在现实世界部署期间，在柔顺控制下对选定手指的接触失败进行物理修正，而冻结的基础策略继续控制其余手指。这些部署结合了基础策略执行、人工修正的手指运动和指尖力观测。我们根据这些部署重建力信息目标，通过行为克隆训练一个独立的力条件策略。该设计减少了人工修正工作量，实现了从现实交互中学习接触调节，并在无需触觉仿真或复杂全手遥操作的情况下，将力反馈引入仅本体感觉的策略。我们在真实硬件上对两个具有挑战性、接触密集的灵巧操作任务评估了ReDex。与仿真到现实迁移的基础策略相比，ReDex在两个物体上的物体翻转成功率从14%提高到86%，在三个物体上的平均螺丝刀旋转进度从26.0%提高到95.3%。
英文摘要
Dexterous manipulation policies trained in simulation often fail to transfer to the real world because of errors in contact timing and force regulation. Yet these policies can retain useful multi-finger coordination for task progression. We propose ReDex, a framework for adapting a simulation-trained base policy to the real world by correcting local contact failures and incorporating tactile feedback. Starting from a proprioception-only base policy, ReDex allows a human operator to physically correct contact failures at selected fingers under compliant control during real-world rollouts, while the frozen base policy continues to control the remaining fingers. These rollouts combine base policy execution, human-corrected finger motion, and fingertip force observations. We reconstruct force-informed targets from these rollouts to train a standalone force-conditioned policy via behavior cloning. This design reduces human correction effort, enables learning of contact regulation from real-world interaction, and introduces force feedback into a proprioception-only policy without tactile simulation or complex full-hand teleoperation. We evaluate ReDex on two challenging, contact-rich dexterous manipulation tasks on real hardware. Compared with sim-to-real transferred base policies, ReDex increases Object Flipping success rate from 14\% to 86\% across two objects and average Screwdriver Rotation progress from 26.0% to 95.3% across three objects.
