CityWalker: Web規模の動画から身体性を伴う都市ナビゲーションを学習
CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
Web上の街歩き・運転動画から行動教師信号を抽出し、地図なし・路上外でも動ける都市ナビゲーション方策を大規模模倣学習で獲得した研究。
著者: Xinhao Liu, Jintong Li, Yicheng Jiang, Niranjan Sujay, Zhicheng Yang, Juexiao Zhang, John Abanes, Jing Zhang, Chen Feng
分類: cs.CV, cs.RO
原文アブストラクト
Navigating dynamic urban environments presents significant challenges for embodied agents, requiring advanced spatial reasoning and adherence to common-sense norms. Despite progress, existing visual navigation methods struggle in map-free or off-street settings, limiting the deployment of autonomous agents like last-mile delivery robots. To overcome these obstacles, we propose a scalable, data-driven approach for human-like urban navigation by training agents on thousands of hours of in-the-wild city walking and driving videos sourced from the web. We introduce a simple and scalable data processing pipeline that extracts action supervision from these videos, enabling large-scale imitation learning without costly annotations. Our model learns sophisticated navigation policies to handle diverse challenges and critical scenarios. Experimental results show that training on large-scale, diverse datasets significantly enhances navigation performance, surpassing current methods. This work shows the potential of using abundant online video data to develop robust navigation policies for embodied agents in dynamic urban settings. Project homepage is at https://ai4ce.github.io/CityWalker/.
