人間の一人称視点動画から異なる身体性を超えた視覚表現を学習するEgo-CEVR
Ego-CEVR: Learning Cross-Embodiment Visual Representations from Human Egocentric Videos
人間の一人称視点動画で大域的なタスク理解を、ロボットの手首観測と行動教師で細粒度の操作を別々に学習し、両表現を行動ポリシーに統合する枠組みを提案した。
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: Keru Zhou, Zhirui Fang, Xinrun Xu, Yaopeng Lou, Zeyuan He, Zihao Zhu, Xinze Niu, Chen Wang, Tianfu Li, Samith Va, Bin Qian, Junwei Li, Wenjia Ding, Yicheng Xu, Chang Zhou, Ziwei Wang, Li Liu, Xiu Li, Maoqing Yao
分類: cs.RO
原文アブストラクト
As egocentric video becomes increasingly available for embodied learning, an important research question is how to turn this low-cost, scalable source of data into robot manipulation capabilities. Egocentric videos naturally provide rich context for high-level task understanding, while real-robot demonstrations with wrist observations and action annotations provide supervision for fine-grained action alignment. We present Ego-CEVR, a data-native framework for hierarchical visual representation learning that assigns distinct learning objectives to global and interaction representations. The global module learns object relations, task state, and temporal progress through future prediction on egocentric video. The Interaction module interprets wrist observations in global context and learns local alignment and contact cues through robot action supervision. Separate residual paths expose both representations to the action policy, preserving direct access to task context alongside fine-grained execution information. Ego-CEVR supports independent pretraining of its global video module on large-scale human egocentric videos and videos from diverse robot embodiments, without requiring robot action labels or paired wrist observations.