CityWalker
- AI model
- Navigation and mapping
CityWalker is a learned navigation model that trains urban walking agents by imitation learning from thousands of hours of online city walking and driving videos.
- Stale
Made by AI4CE Lab @ NYU, United States (checked on github.com/ai4ce (opens in a new tab)).
Source on GitHub: github.com/ai4ce/CityWalker (opens in a new tab). Facts read at commit ab0ef60 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit ab0ef60 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
Labels
- StaleNo commit in 12 months: the newest is from 5 Aug 2025.
What it does
- Trains embodied urban navigation agents from web-scale city walking and driving videos using scalable, data-driven imitation learning.
- Provides training, fine-tuning and testing scripts driven by YAML configuration files.
- Offers a pretrained model in the project's releases tab.
- Builds on the ViNT and NoMaD open-source navigation implementations.
Written by Robotheca from the project's README (opens in a new tab) at commit ab0ef60.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Stale: no commit in 12 months
- Newest commit
- 5 Aug 2025 on main
- Latest release
- CityWalker V1.0 (23 Nov 2024)
Checked on GitHub on 16 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.