実世界動画からのスケーラブル学習による都市ナビゲーションのロングテール顕在化
Exposing the Long-tail in Embodied Urban Navigation via Scalable Learning from In-the-Wild Videos
ウェブ上の未編集な一人称視点動画からメトリック軌跡とナビゲーション意味情報を自動アノテーションし、視覚言語行動ポリシーを訓練して都市ナビゲーションのロングテールな稀なシナリオを体系的に明らかに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: Bingyi Xia, Han Bao, Zhewei Chen, Hanjing Ye, Jingwen Yu, Yuhan Pang, Wenjun Xu, Jiankun Wang
分類: cs.RO
原文アブストラクト
Learning embodied urban navigation policies from real-world data is constrained by the cost of task-specific data collection and the limited coverage of rare yet safety-critical scenarios. To address these challenges, we present a scalable framework for learning point-goal urban navigation from web-scale in-the-wild egocentric videos while systematically exposing its long tail. The framework automatically annotates uncurated web videos with metric trajectories and structured navigation semantics, which are then used to train a vision-language-action policy for interpretable navigation planning. We characterize the long tail based on model performance and the distribution of perception-motion patterns, and employ reflection-based analysis to diagnose recurring failure modes. Experiments on web-video data and real-world urban navigation tasks demonstrate effective knowledge transfer from unconstrained videos and reveal coherent long-tail structures beyond aggregate navigation performance.