ハンド・アイ自律配送：ヒューマノイドのナビゲーション・歩行・リーチングの学習
Hand-Eye Autonomous Delivery: Learning Humanoid Navigation, Locomotion and Reaching
人間の動作と視覚データからヒューマノイドのナビゲーション・歩行・リーチングを学習するモジュール型フレームワークHEADを提案し、実世界で有効性を示した。
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: Sirui Chen, Yufei Ye, Zi-Ang Cao, Jennifer Lew, Pei Xu, C. Karen Liu
分類: cs.RO
原文アブストラクト
We propose Hand-Eye Autonomous Delivery (HEAD), a framework that learns navigation, locomotion, and reaching skills for humanoids, directly from human motion and vision perception data. We take a modular approach where the high-level planner commands the target position and orientation of the hands and eyes of the humanoid, delivered by the low-level policy that controls the whole-body movements. Specifically, the low-level whole-body controller learns to track the three points (eyes, left hand, and right hand) from existing large-scale human motion capture data while high-level policy learns from human data collected by Aria glasses. Our modular approach decouples the ego-centric vision perception from physical actions, promoting efficient learning and scalability to novel scenes. We evaluate our method both in simulation and in the real-world, demonstrating humanoid's capabilities to navigate and reach in complex environments designed for humans.
