{"id":18600768,"url":"https://github.com/autonomousvision/navsim","last_synced_at":"2025-05-16T00:06:23.284Z","repository":{"id":223468638,"uuid":"745836406","full_name":"autonomousvision/navsim","owner":"autonomousvision","description":"[NeurIPS 2024] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking","archived":false,"fork":false,"pushed_at":"2025-04-24T21:10:29.000Z","size":35403,"stargazers_count":473,"open_issues_count":6,"forks_count":41,"subscribers_count":15,"default_branch":"main","last_synced_at":"2025-04-24T22:28:59.163Z","etag":null,"topics":["autonomous-driving","planning","self-driving"],"latest_commit_sha":null,"homepage":"","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/autonomousvision.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}},"created_at":"2024-01-20T09:42:31.000Z","updated_at":"2025-04-24T21:10:33.000Z","dependencies_parsed_at":"2024-02-20T12:31:46.161Z","dependency_job_id":"e97b9242-d9c5-4c10-b9bc-ffb5b82e4556","html_url":"https://github.com/autonomousvision/navsim","commit_stats":{"total_commits":29,"total_committers":5,"mean_commits":5.8,"dds":0.5862068965517242,"last_synced_commit":"4a5584606a1f75e6e48984cabfde5cddd5685a3c"},"previous_names":["autonomousvision/navsim"],"tags_count":11,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autonomousvision%2Fnavsim","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autonomousvision%2Fnavsim/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autonomousvision%2Fnavsim/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autonomousvision%2Fnavsim/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/autonomousvision","download_url":"https://codeload.github.com/autonomousvision/navsim/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254442854,"owners_count":22071878,"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","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":["autonomous-driving","planning","self-driving"],"created_at":"2024-11-07T02:05:18.300Z","updated_at":"2025-05-16T00:06:18.251Z","avatar_url":"https://github.com/autonomousvision.png","language":"Python","funding_links":[],"categories":["Papers","Autonomous Driving"],"sub_categories":["Social \u0026 Human-Robot Interaction"],"readme":"\u003cdiv id=\"top\" align=\"center\"\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/navsim_transparent.png\" width=\"600\"\u003e\n  \u003ch2 align=\"center\"\u003eData-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking\u003c/h1\u003e\n  \u003ch3 align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/2406.15349\"\u003ePaper\u003c/a\u003e | \u003ca href=\"https://danieldauner.github.io/assets/pdf/Dauner2024NIPS_supplementary.pdf\"\u003eSupplementary\u003c/a\u003e | \u003ca href=\"https://www.youtube.com/watch?v=Qe76HRmPDe0\"\u003eTalk\u003c/a\u003e | \u003ca href=\"https://opendrivelab.com/challenge2024/#end_to_end_driving_at_scale\"\u003e2024 Challenge\u003c/a\u003e | \u003ca href=\"https://huggingface.co/spaces/AGC2024-P/e2e-driving-navsim\"\u003eLeaderboard v1.1\u003c/a\u003e | \u003ca href=\"https://huggingface.co/spaces/AGC2025/e2e-driving-warmup\"\u003eWarmup Leaderboard v2.0\u003c/a\u003e \u003c/h3\u003e\n\u003c/p\u003e\n\n\u003c/div\u003e\n\n\u003cbr/\u003e\n\n\n\u003e [**NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking**](https://arxiv.org/abs/2406.15349)\n\u003e\n\u003e [Daniel Dauner](https://danieldauner.github.io/)\u003csup\u003e1,2\u003c/sup\u003e, [Marcel Hallgarten](https://mh0797.github.io/)\u003csup\u003e1,5\u003c/sup\u003e, [Tianyu Li](https://github.com/sephyli)\u003csup\u003e3\u003c/sup\u003e, [Xinshuo Weng](https://xinshuoweng.com/)\u003csup\u003e4\u003c/sup\u003e, [Zhiyu Huang](https://mczhi.github.io/)\u003csup\u003e4,6\u003c/sup\u003e, [Zetong Yang](https://scholar.google.com/citations?user=oPiZSVYAAAAJ)\u003csup\u003e3\u003c/sup\u003e\\\n\u003e [Hongyang Li](https://lihongyang.info/)\u003csup\u003e3\u003c/sup\u003e, [Igor Gilitschenski](https://www.gilitschenski.org/igor/)\u003csup\u003e7,8\u003c/sup\u003e, [Boris Ivanovic](https://www.borisivanovic.com/)\u003csup\u003e4\u003c/sup\u003e, [Marco Pavone](https://web.stanford.edu/~pavone/)\u003csup\u003e4,9\u003c/sup\u003e, [Andreas Geiger](https://www.cvlibs.net/)\u003csup\u003e1,2\u003c/sup\u003e, and [Kashyap Chitta](https://kashyap7x.github.io/)\u003csup\u003e1,2\u003c/sup\u003e  \u003cbr\u003e\n\u003e\n\u003e \u003csup\u003e1\u003c/sup\u003eUniversity of Tübingen, \u003csup\u003e2\u003c/sup\u003eTübingen AI Center, \u003csup\u003e3\u003c/sup\u003eOpenDriveLab at Shanghai AI Lab, \u003csup\u003e4\u003c/sup\u003eNVIDIA Research\\\n\u003e \u003csup\u003e5\u003c/sup\u003eRobert Bosch GmbH, \u003csup\u003e6\u003c/sup\u003eNanyang Technological University, \u003csup\u003e7\u003c/sup\u003eUniversity of Toronto, \u003csup\u003e8\u003c/sup\u003eVector Institute, \u003csup\u003e9\u003c/sup\u003eStanford University\n\u003e\n\u003e Advances in Neural Information Processing Systems (NeurIPS), 2024 \\\n\u003e Track on Datasets and Benchmarks\n\u003cbr/\u003e\n\n\n## Highlights \u003ca name=\"highlight\"\u003e\u003c/a\u003e\n\n🔥 NAVSIM gathers simulation-based metrics (such as progress and time to collision) for end-to-end driving by unrolling simplified bird's eye view abstractions of scenes for a short simulation horizon. It operates under the condition that the policy has limited influence on the environment, which enables **efficient, open-loop metric computation** while being **better aligned with closed-loop** evaluations than traditional displacement errors.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/navsim_cameras.gif\" width=\"800\"\u003e\n\u003c/p\u003e\n\n## Table of Contents\n1. [Highlights](#highlight)\n2. [Getting started](#gettingstarted)\n3. [Changelog](#changelog)\n4. [License and citation](#licenseandcitation)\n5. [Other resources](#otherresources)\n\n\n## Getting started \u003ca name=\"gettingstarted\"\u003e\u003c/a\u003e\n\n- [Download and installation](docs/install.md)\n- [Understanding and creating agents](docs/agents.md)\n- [Understanding the data format and classes](docs/cache.md)\n- [Dataset splits vs. filtered training / test splits](docs/splits.md)\n- [Understanding the Extended PDM Score](docs/metrics.md)\n- [Understanding the traffic simulation](docs/traffic_agents.md)\n- [Submitting to the Leaderboard](docs/submission.md)\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\n## Changelog \u003ca name=\"changelog\"\u003e\u003c/a\u003e\n- **`[2025/02/28]`** NAVSIM v2.0 release (official devkit version for 2025 warm-up phase)\n  - Extends the PDM Score with more metrics and penalties (see [metrics](docs/metrics.md))\n  - Adds a new two-stage pseudo closed-loop simulation (see [metrics](docs/metrics.md))\n  - Adds support for reactive traffic agent policies (see [traffic simulation](docs/metrics.md))\n- **`[2024/09/03]`** NAVSIM v1.1 release\n  - Leaderboard for `navtest` on [Hugging Face](https://huggingface.co/spaces/AGC2024-P/e2e-driving-navsim)\n  - Release of baseline checkpoints on [Hugging Face](https://huggingface.co/autonomousvision/navsim_baselines)\n  - Updated docs for [submission](docs/submission.md) and [paper](https://arxiv.org/abs/2406.15349)\n  - Code refactoring, formatting, minor fixes\n- **`[2024/04/21]`** NAVSIM v1.0 release (official devkit version for [AGC 2024](https://opendrivelab.com/challenge2024/#end_to_end_driving_at_scale))\n  - Parallelization of metric caching / evaluation\n  - Adds [Transfuser](https://arxiv.org/abs/2205.15997) baseline (see [agents](docs/agents.md#Baselines))\n  - Adds standardized training and test filtered splits (see [splits](docs/splits.md))\n  - Visualization tools (see [tutorial_visualization.ipynb](tutorial/tutorial_visualization.ipynb))\n- **`[2024/04/03]`** NAVSIM v0.4 release\n  - Support for test phase frames of competition\n  - Download script for trainval\n  - Egostatus MLP Agent and training pipeline\n- **`[2024/03/25]`** NAVSIM v0.3 release (official devkit version for warm-up phase)\n  - Adds code for Leaderboard submission\n- **`[2024/03/11]`** NAVSIM v0.2 release\n  - Easier installation and download\n  - mini and test data split integration\n  - Privileged `Human` agent\n- **`[2024/02/20]`** NAVSIM v0.1 release (initial demo)\n  - OpenScene-mini sensor blobs and annotation logs\n  - Naive `ConstantVelocity` agent\n\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\n## License and citation \u003ca name=\"licenseandcitation\"\u003e\u003c/a\u003e\nAll assets and code in this repository are under the [Apache 2.0 license](./LICENSE) unless specified otherwise. The datasets (including nuPlan and OpenScene) inherit their own distribution licenses. Please consider citing our paper and project if they help your research.\n\n```BibTeX\n@inproceedings{Dauner2024NEURIPS,\n\tauthor = {Daniel Dauner and Marcel Hallgarten and Tianyu Li and Xinshuo Weng and Zhiyu Huang and Zetong Yang and Hongyang Li and Igor Gilitschenski and Boris Ivanovic and Marco Pavone and Andreas Geiger and Kashyap Chitta},\n\ttitle = {NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking},\n\tbooktitle = {Advances in Neural Information Processing Systems (NeurIPS)},\n\tyear = {2024},\n}\n```\n\n```BibTeX\n@misc{Contributors2024navsim,\n    title={NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking},\n    author={NAVSIM Contributors},\n    howpublished={\\url{https://github.com/autonomousvision/navsim}},\n    year={2024}\n}\n```\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\n## Other resources \u003ca name=\"otherresources\"\u003e\u003c/a\u003e\n\n- [SLEDGE](https://github.com/autonomousvision/sledge) | [tuPlan garage](https://github.com/autonomousvision/tuplan_garage) | [CARLA garage](https://github.com/autonomousvision/carla_garage) | [Survey on E2EAD](https://github.com/OpenDriveLab/End-to-end-Autonomous-Driving)\n- [PlanT](https://github.com/autonomousvision/plant) | [KING](https://github.com/autonomousvision/king) | [TransFuser](https://github.com/autonomousvision/transfuser) | [NEAT](https://github.com/autonomousvision/neat)\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautonomousvision%2Fnavsim","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fautonomousvision%2Fnavsim","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautonomousvision%2Fnavsim/lists"}