ActiveGlasses: 自己中心的な人間のデモから能動視覚で操作を学習する
ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration
スマートグラスに取り付けたステレオカメラで人間のデモを収集し、同じカメラをロボットの知覚アームに搭載して能動視覚を再現することで、ロボット操作をゼロショット転移で学習するシステムを提案した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yanwen Zou, Chenyang Shi, Wenye Yu, Han Xue, Jun Lv, Ye Pan, Chuan Wen, Cewu Lu
分類: cs.RO
原文アブストラクト
Large-scale real-world robot data collection is a prerequisite for bringing robots into everyday deployment. However, existing pipelines often rely on specialized handheld devices to bridge the embodiment gap, which not only increases operator burden and limits scalability, but also makes it difficult to capture the naturally coordinated perception-manipulation behaviors of human daily interaction. This challenge calls for a more natural system that can faithfully capture human manipulation and perception behaviors while enabling zero-shot transfer to robotic platforms. We introduce ActiveGlasses, a system for learning robot manipulation from ego-centric human demonstrations with active vision. A stereo camera mounted on smart glasses serves as the sole perception device for both data collection and policy inference: the operator wears it during bare-hand demonstrations, and the same camera is mounted on a 6-DoF perception arm during deployment to reproduce human active vision. To enable zero-transfer, we extract object trajectories from demonstrations and use an object-centric point-cloud policy to jointly predict manipulation and head movement. Across several challenging tasks involving occlusion and precise interaction, ActiveGlasses achieves zero-shot transfer with active vision, consistently outperforms strong baselines under the same hardware setup, and generalizes across two robot platforms.
