{"id":37066913,"url":"https://github.com/oatml/oatomobile","last_synced_at":"2026-01-14T07:51:14.939Z","repository":{"id":50092685,"uuid":"272983534","full_name":"OATML/oatomobile","owner":"OATML","description":"A research framework for autonomous driving","archived":false,"fork":false,"pushed_at":"2023-07-06T22:00:12.000Z","size":7856,"stargazers_count":201,"open_issues_count":14,"forks_count":37,"subscribers_count":9,"default_branch":"alpha","last_synced_at":"2025-12-06T04:26:12.079Z","etag":null,"topics":["autonomous-driving","carla-simulator","imitation-learning"],"latest_commit_sha":null,"homepage":"https://sites.google.com/view/av-detect-recover-adapt","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/OATML.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}},"created_at":"2020-06-17T13:37:40.000Z","updated_at":"2025-10-29T13:45:47.000Z","dependencies_parsed_at":"2022-08-31T06:41:58.903Z","dependency_job_id":null,"html_url":"https://github.com/OATML/oatomobile","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/OATML/oatomobile","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OATML%2Foatomobile","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OATML%2Foatomobile/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OATML%2Foatomobile/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OATML%2Foatomobile/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OATML","download_url":"https://codeload.github.com/OATML/oatomobile/tar.gz/refs/heads/alpha","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OATML%2Foatomobile/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28413511,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T05:26:33.345Z","status":"ssl_error","status_checked_at":"2026-01-14T05:21:57.251Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["autonomous-driving","carla-simulator","imitation-learning"],"created_at":"2026-01-14T07:51:14.272Z","updated_at":"2026-01-14T07:51:14.919Z","avatar_url":"https://github.com/OATML.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# OATomobile: A research framework for autonomous driving\n\n  **[Overview](#overview)**\n| **[Installation](#installation)**\n| **[Baselines]**\n| **[Paper]**\n\n![PyPI Python Version](https://img.shields.io/pypi/pyversions/oatomobile)\n![PyPI version](https://badge.fury.io/py/oatomobile.svg)\n[![arXiv](https://img.shields.io/badge/arXiv-2006.14911-b31b1b.svg)](https://arxiv.org/abs/2006.14911)\n[![GitHub license](https://img.shields.io/pypi/l/oatomobile)](./LICENSE)\n\nOATomobile is a library for autonomous driving research.\nOATomobile strives to expose simple, efficient, well-tuned and readable agents, that serve both as reference implementations of popular algorithms and as strong baselines, while still providing enough flexibility to do novel research.\n\n## Overview\n\nIf you just want to get started using OATomobile quickly, the first thing to know about the framework is that we wrap [CARLA] towns and scenarios in OpenAI [gym]s:\n\n```python\nimport oatomobile\n\n# Initializes a CARLA environment.\nenvironment = oatomobile.envs.CARLAEnv(town=\"Town01\")\n\n# Makes an initial observation.\nobservation = environment.reset()\ndone = False\n\nwhile not done:\n  # Selects a random action.\n  action = environment.action_space.sample()\n  observation, reward, done, info = environment.step(action)\n\n  # Renders interactive display.\n  environment.render(mode=\"human\")\n\n# Book-keeping: closes\nenvironment.close()\n```\n\n[Baselines] can also be used out-of-the-box:\n\n```python\n# Rule-based agents.\nimport oatomobile.baselines.rulebased\n\nagent = oatomobile.baselines.rulebased.AutopilotAgent(environment)\naction = agent.act(observation)\n\n# Imitation-learners.\nimport torch\nimport oatomobile.baselines.torch\n\nmodels = [oatomobile.baselines.torch.ImitativeModel() for _ in range(4)]\nckpts = ... # Paths to the model checkpoints.\nfor model, ckpt in zip(models, ckpts):\n  model.load_state_dict(torch.load(ckpt))\nagent = oatomobile.baselines.torch.RIPAgent(\n  environment=environment,\n  models=models,\n  algorithm=\"WCM\",\n)\naction = agent.act(observation)\n```\n\n## Installation\n\nWe have tested OATomobile on Python 3.5.\n\n1.  To install the core libraries (including [CARLA], the backend simulator):\n\n    ```bash\n    # The path to download CARLA 0.9.6.\n    export CARLA_ROOT=...\n    mkdir -p $CARLA_ROOT\n\n    # Downloads hosted binaries.\n    wget http://carla-assets-internal.s3.amazonaws.com/Releases/Linux/CARLA_0.9.6.tar.gz\n\n    # CARLA 0.9.6 installation.\n    tar -xvzf CARLA_0.9.6.tar.gz -C $CARLA_ROOT\n\n    # Installs CARLA 0.9.6 Python API.\n    easy_install $CARLA_ROOT/PythonAPI/carla/dist/carla-0.9.6-py3.5-linux-x86_64.egg\n    ```\n\n1.  To install the OATomobile core API:\n\n    ```bash\n    pip install --upgrade pip setuptools\n    pip install oatomobile\n    ```\n\n1.  To install dependencies for our [PyTorch]- or [TensorFlow]-based agents:\n\n    ```bash\n    pip install oatomobile[torch]\n    # and/or\n    pip install oatomobile[tf]\n    ```\n\n## Citing OATomobile\n\nIf you use OATomobile in your work, please cite the accompanying\n[technical report][Paper]:\n\n```bibtex\n@inproceedings{filos2020can,\n    title={Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?},\n    author={Filos, Angelos and\n            Tigas, Panagiotis and\n            McAllister, Rowan and\n            Rhinehart, Nicholas and\n            Levine, Sergey and\n            Gal, Yarin},\n    booktitle={International Conference on Machine Learning (ICML)},\n    year={2020}\n}\n```\n\n[Baselines]: oatomobile/baselines/\n[Examples]: examples/\n[CARLA]: https://carla.readthedocs.io/\n[Paper]: https://arxiv.org/abs/2006.14911\n[TensorFlow]: https://tensorflow.org\n[PyTorch]: http://pytorch.org\n[gym]: https://github.com/openai/gym\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foatml%2Foatomobile","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Foatml%2Foatomobile","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foatml%2Foatomobile/lists"}