EgoGuide: 以自我为中心引导的高效无机器人演示收集与学习
EgoGuide: Egocentric Guidance for Efficient Robot-Free Demonstration Collection and Learning
AI总结:
提出EgoGuide数据收集接口,通过同步腕部和头部/自我中心观察并在线视觉-几何质量引导,结合门控自我中心残差策略,减少所需数据量并提高数据效率。
摘要:
目前,从真实世界演示中进行的机器人学习受到数据扩展的限制。通用操作接口(UMI)提供了一种高效的无机器人数据收集接口,然而当前的UMI风格流程通常收集冗余的演示,并且缺乏全局场景上下文。为了提高数据效率,我们提出了EgoGuide,一种收集接口,它记录同步的腕部和头部/自我中心观察,并将其与在线视觉-几何数据质量引导相结合。我们还引入了一种门控自我中心残差策略,用于从视角变化的自我中心相机中进行鲁棒学习,允许头部/自我中心上下文纠正模糊的局部观察,同时保持稳定的腕部视角控制。真实世界实验表明,EgoGuide减少了所需的数据集数并提高了数据效率。残差策略进一步提高了视觉遮挡下的鲁棒性。项目页面:此 https URL
英文摘要:
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
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。