{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/carla-an-open-urban-driving-simulator","title":"CARLA: An Open Urban Driving Simulator","arxiv_id":"1711.03938","date":"2017-11-10","proceeding":null,"authors":["Alexey Dosovitskiy","German Ros","Felipe Codevilla","Antonio Lopez","Vladlen Koltun"],"abstract":"We introduce CARLA, an open-source simulator for autonomous driving research.\nCARLA has been developed from the ground up to support development, training,\nand validation of autonomous urban driving systems. In addition to open-source\ncode and protocols, CARLA provides open digital assets (urban layouts,\nbuildings, vehicles) that were created for this purpose and can be used freely.\nThe simulation platform supports flexible specification of sensor suites and\nenvironmental conditions. We use CARLA to study the performance of three\napproaches to autonomous driving: a classic modular pipeline, an end-to-end\nmodel trained via imitation learning, and an end-to-end model trained via\nreinforcement learning. The approaches are evaluated in controlled scenarios of\nincreasing difficulty, and their performance is examined via metrics provided\nby CARLA, illustrating the platform's utility for autonomous driving research.\nThe supplementary video can be viewed at https://youtu.be/Hp8Dz-Zek2E","url_abs":"http://arxiv.org/abs/1711.03938v1","url_pdf":"http://arxiv.org/pdf/1711.03938v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"carla-an-open-urban-driving-simulator","repo_url":"https://github.com/filippogiruzzi/semantic_segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[{"method_slug":"carla","method_name":"CARLA"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[{"slug":"carla","name":"CARLA","full_name":"Car Learning to Act"}],"methods_introduced":[{"slug":"carla","name":"CARLA","full_name":"CARLA: An Open Urban Driving Simulator"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.03938","atlas_url":"https://app.syntology.ai/?focus=1711.03938","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}