用头戴视角提升机器人演示数据效率，减少冗余并增强视觉鲁棒性。
EgoGuide: Egocentric Guidance for Efficient Robot-Free Demonstration Collection and Learning
- 同步记录手腕与头戴视角数据，结合实时质量评估
- 实验表明数据量减少，且在遮挡下仍保持稳定控制
- 适合无机器人场景下的高效示范学习研究
当前机器人从真实世界示范中学习受限于数据规模。通用操作接口（UMI）提供了无需机器人的高效数据采集方式，但现有方法常收集冗余示范且缺乏全局场景上下文。为提升数据效率，我们提出EgoGuide，一种同步记录手腕与头部/第一人称视角观测的采集界面，并耦合在线视觉-几何数据质量引导。同时引入门控第一人称残差策略，利用头戴视角上下文修正局部观测模糊，同时保持稳定的手腕视角控制。真实世界实验表明，EgoGuide可减少所需数据集数量，提升数据效率；残差策略在视觉遮挡下进一步增强鲁棒性。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。