Robot learning from real-world demonstrations is currently constrained by data scaling. Universal Manipulation Interface (UMI) provides an efficient robot-free data collection interface, yet current UMI-style pipelines often collect redundant demonstrations and lack global scene context. To improve data efficiency, we present EgoGuide, a collection interface that records synchronized wrist and head/egocentric observations and couples them with online visual-geometric data quality guidance. We also introduce a Gated Egocentric Residual Policy for robust learning from a viewpoint-varying egocentric camera, allowing head/egocentric context to correct ambiguous local observations while preserving stable wrist-view control. Real-world experiments show that EgoGuide reduces the required number of data episodes and improves data efficiency. The residual policy further improves robustness under visual occlusion. Project Page: https://silicx.github.io/EgoGuide

翻译：从真实世界演示中进行机器人学习目前受限于数据规模扩展。通用操作接口（Universal Manipulation Interface, UMI）提供了一种高效的无机器人数据采集接口，但现有UMI类流程常采集冗余演示，且缺乏全局场景上下文。为提升数据效率，我们提出EgoGuide——一种同步记录腕部与头部/自我中心观测，并耦合在线视觉-几何数据质量引导的采集接口。同时，我们引入门控自我中心残差策略（Gated Egocentric Residual Policy），用于从视角可变的自我中心相机进行鲁棒学习，使头部/自我中心上下文能够修正模糊的局部观测，同时保持稳定的腕部视角控制。真实世界实验表明，EgoGuide可减少所需数据回合数并提升数据效率。该残差策略进一步增强了视觉遮挡下的鲁棒性。项目页面：https://silicx.github.io/EgoGuide