We propose an object-centric recovery policy framework to address the challenges of out-of-distribution (OOD) scenarios in visuomotor policy learning. Previous behavior cloning (BC) methods rely heavily on a large amount of labeled data coverage, failing in unfamiliar spatial states. Without relying on extra data collection, our approach learns a recovery policy constructed by an inverse policy inferred from object keypoint manifold gradient in the original training data. The recovery policy serves as a simple add-on to any base visuomotor BC policy, agnostic to a specific method, guiding the system back towards the training distribution to ensure task success even in OOD situations. We demonstrate the effectiveness of our object-centric framework in both simulation and real robot experiments, achieving an improvement of $\textbf{77.7\%}$ over the base policy in OOD. Project Website: https://sites.google.com/view/ocr-penn

本研究针对视觉运动策略学习中的分布外（OOD）场景挑战提出了一种物体中心的恢复策略框架。与以往依赖大量标注数据的行为克隆方法不同，我们的方法通过从原始训练数据中推断物体关键点流形梯度构建逆向策略来学习恢复策略，从而无需额外数据收集。这一恢复策略可以作为任何基于视觉运动行为克隆的基础策略的简单附加部分，引导系统重新回到训练分布，即使在OOD情境下也能确保任务成功。

面向物体中心的逆向策略恢复框架：视觉运动模仿学习中的分布外恢复