CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
This work addresses the challenge of map-free or off-street navigation for autonomous agents like delivery robots, though it is incremental as it builds on existing imitation learning approaches with a scalable data-driven method.
The paper tackles the problem of enabling embodied agents to navigate dynamic urban environments by training them on thousands of hours of web-sourced city videos, resulting in significantly enhanced navigation performance that surpasses current methods.
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/.