{"id":24396799,"url":"https://github.com/ai4ce/citywalker","last_synced_at":"2025-07-24T01:35:03.084Z","repository":{"id":265170166,"uuid":"868718822","full_name":"ai4ce/CityWalker","owner":"ai4ce","description":"[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos","archived":false,"fork":false,"pushed_at":"2025-04-03T16:48:39.000Z","size":86861,"stargazers_count":106,"open_issues_count":1,"forks_count":6,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-06-27T14:03:46.440Z","etag":null,"topics":["cvpr2025","embodied-ai","embodied-navigation","imitation-learning","outdoor-navigation","point-goal-navigation","quadruped","robot-learning","scaling-law","urban-navigation","video-learning","visual-navigation"],"latest_commit_sha":null,"homepage":"https://ai4ce.github.io/CityWalker/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ai4ce.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-10-07T04:03:21.000Z","updated_at":"2025-06-27T13:13:43.000Z","dependencies_parsed_at":"2025-04-11T16:52:52.972Z","dependency_job_id":"7e915832-8ed4-49d9-917b-bc0839fc0c0a","html_url":"https://github.com/ai4ce/CityWalker","commit_stats":null,"previous_names":["ai4ce/citywalker"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/ai4ce/CityWalker","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FCityWalker","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FCityWalker/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FCityWalker/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FCityWalker/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ai4ce","download_url":"https://codeload.github.com/ai4ce/CityWalker/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FCityWalker/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266779642,"owners_count":23982947,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-23T02:00:09.312Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cvpr2025","embodied-ai","embodied-navigation","imitation-learning","outdoor-navigation","point-goal-navigation","quadruped","robot-learning","scaling-law","urban-navigation","video-learning","visual-navigation"],"created_at":"2025-01-19T21:58:30.607Z","updated_at":"2025-07-24T01:35:03.062Z","avatar_url":"https://github.com/ai4ce.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [CVPR 2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos\n\n### TL;DR: CityWalker leverages thousands of hours of online city walking and driving videos to train autonomous agents for robust, generalizable navigation in dynamic urban environments through scalable, data-driven imitation learning.\n\n\u003ca href='https://arxiv.org/abs/2411.17820'\u003e\u003cimg src='https://img.shields.io/badge/Paper-arXiv-red'\u003e\u003c/a\u003e \u003ca href='https://ai4ce.github.io/CityWalker/'\u003e\u003cimg src='https://img.shields.io/badge/Project-hompage-green'\u003e\u003c/a\u003e \u003ca href='https://huggingface.co/datasets/ai4ce/CityWalker'\u003e\u003cimg src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Dataset-blue'\u003e\u003c/a\u003e\n\n[Xinhao Liu](https://gaaaavin.github.io/)\\*,\n[Jintong Li](.)\\*, \n[Yicheng Jiang](.),\n[Niranjan Sujay](.),\n[Zhicheng Ynag](.),\n[Juexiao Zhang](https://juexzz.github.io/),\n[John Abanes](.),\n[Jing Zhang](https://jingz6676.github.io/), \n[Chen Feng](https://engineering.nyu.edu/faculty/chen-feng)†\n\n![](./src/nav.gif)\n\n**Checkout a mosaic demo of our dataset:**\n\nhttps://github.com/user-attachments/assets/02f57a2b-f2d2-4638-a8b0-d837d219735f\n\n\n\n# Getting Started\n## Installation\nThe project should be compatible with latest Pytorch and CUDA versions. The code is tested with Python 3.11, PyTorch 2.5.0, and CUDA 12.1. To install the dependencies, run:\n```\nconda env create -f environment.yml\nconda activate citywalker\n```\n\n## Data Preparation\nPlease see [dataset/README.md](./dataset/README.md) for details on how to prepare the dataset.\n\n## Training\nTo train the model, run:\n```\npython train.py --config config/citywalk_2000hr.yaml\n```\nWe provide our **pretrained model** in the [releases tab](https://github.com/ai4ce/CityWalker/releases).\n\n## Fine-tuning\nTo fine-tune the model, run:\n```\npython fine_tune.py --config config/finetune.yaml --checkpoint \u003cpath_to_checkpoint\u003e\n```\n\n## Testing\nTo test the model, run:\n```\npython test.py --config config/finetune.yaml --checkpoint \u003cpath_to_checkpoint\u003e\n```\n\n# Citation\n```\n@article{liu2024citywalker,\n  title={CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos},\n  author={Liu, Xinhao and Li, Jintong and Jiang, Yicheng and Sujay, Niranjan and Yang, Zhicheng and Zhang, Juexiao and Abanes, John and Zhang, Jing and Feng, Chen},\n  journal={arXiv preprint arXiv:2411.17820},\n  year={2024}\n}\n```\n\n# Acknowledgements\nThe work was supported by NSF grants 2238968, 2121391, 2322242 and 2345139; and in part through the NYU IT High Performance Computing resources, services, and staff expertise. We thank Xingyu Liu and Zixuan Hu for their help in data collection.\n\nWe also thank the authors of the following repositories for their open-source implementations:\n* [ViNT: A Foundation Model for Visual Navigation](https://github.com/robodhruv/visualnav-transformer), CoRL 2023\n* [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://github.com/robodhruv/visualnav-transformer), ICRA 2024\n\n\u003ca href=\"https://star-history.com/#ai4ce/citywalker\u0026Date\"\u003e\n \u003cpicture\u003e\n   \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"https://api.star-history.com/svg?repos=ai4ce/citywalker\u0026type=Date\u0026theme=dark\" /\u003e\n   \u003csource media=\"(prefers-color-scheme: light)\" srcset=\"https://api.star-history.com/svg?repos=ai4ce/citywalker\u0026type=Date\" /\u003e\n   \u003cimg alt=\"Star History Chart\" src=\"https://api.star-history.com/svg?repos=ai4ce/citywalker\u0026type=Date\" /\u003e\n \u003c/picture\u003e\n\u003c/a\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fai4ce%2Fcitywalker","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fai4ce%2Fcitywalker","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fai4ce%2Fcitywalker/lists"}