{"id":13443285,"url":"https://github.com/OpenDriveLab/TCP","last_synced_at":"2025-03-20T16:31:03.165Z","repository":{"id":37299533,"uuid":"504117044","full_name":"OpenDriveLab/TCP","owner":"OpenDriveLab","description":"[NeurIPS 2022] Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline.","archived":false,"fork":false,"pushed_at":"2024-08-06T07:52:37.000Z","size":11054,"stargazers_count":403,"open_issues_count":25,"forks_count":50,"subscribers_count":12,"default_branch":"main","last_synced_at":"2025-03-19T19:08:14.564Z","etag":null,"topics":["carla-driving-simulator","end-to-end-autonomous-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/OpenDriveLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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},"funding":{"github":["OpenDriveLab"],"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"lfx_crowdfunding":null,"custom":null}},"created_at":"2022-06-16T10:48:13.000Z","updated_at":"2025-03-13T16:15:08.000Z","dependencies_parsed_at":"2023-02-08T08:46:17.245Z","dependency_job_id":"3b53d481-1de0-4326-82b7-e4fa12627381","html_url":"https://github.com/OpenDriveLab/TCP","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FTCP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FTCP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FTCP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FTCP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OpenDriveLab","download_url":"https://codeload.github.com/OpenDriveLab/TCP/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244649797,"owners_count":20487494,"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":["carla-driving-simulator","end-to-end-autonomous-driving"],"created_at":"2024-07-31T03:01:58.641Z","updated_at":"2025-03-20T16:31:00.034Z","avatar_url":"https://github.com/OpenDriveLab.png","language":"Python","funding_links":["https://github.com/sponsors/OpenDriveLab"],"categories":["Python"],"sub_categories":[],"readme":"# TCP - Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline\n\n![teaser](assets/teaser_.png)\n\n\u003e Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline  \n\u003e [Penghao Wu*](https://scholar.google.com/citations?user=9mssd5EAAAAJ\u0026hl=en), [Xiaosong Jia*](https://jiaxiaosong1002.github.io/), [Li Chen*](https://scholar.google.com/citations?user=ulZxvY0AAAAJ\u0026hl=en), [Junchi Yan](https://thinklab.sjtu.edu.cn/), [Hongyang Li](https://lihongyang.info/), [Yu Qiao](http://mmlab.siat.ac.cn/yuqiao/)    \n\u003e  - [arXiv Paper](https://arxiv.org/abs/2206.08129), NeurIPS 2022\n\u003e  - [Blog in Chinese](https://zhuanlan.zhihu.com/p/532665469)\n\n\t\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/trajectory-guided-control-prediction-for-end/autonomous-driving-on-carla-leaderboard)](https://paperswithcode.com/sota/autonomous-driving-on-carla-leaderboard?p=trajectory-guided-control-prediction-for-end)\n\nThis repository contains the code for the paper [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://arxiv.org/abs/2206.08129).\n\n\nTCP is a simple unified framework to combine trajectory and control prediction for end-to-end autonomous driving.  By time of release in June 17 2022, our method achieves new state-of-the-art on [CARLA AD Leaderboard](https://leaderboard.carla.org/leaderboard/), in which we rank the **first** in terms of the Driving Score and Infraction Penalty using only a single camera as input. \n\n\n## Setup\nDownload and setup CARLA 0.9.10.1\n```\nmkdir carla\ncd carla\nwget https://carla-releases.s3.eu-west-3.amazonaws.com/Linux/CARLA_0.9.10.1.tar.gz\nwget https://carla-releases.s3.eu-west-3.amazonaws.com/Linux/AdditionalMaps_0.9.10.1.tar.gz\ntar -xf CARLA_0.9.10.1.tar.gz\ntar -xf AdditionalMaps_0.9.10.1.tar.gz\nrm CARLA_0.9.10.1.tar.gz\nrm AdditionalMaps_0.9.10.1.tar.gz\ncd ..\n```\n\nClone this repo and build the environment\n\n```\ngit clone https://github.com/OpenPerceptionX/TCP.git\ncd TCP\nconda env create -f environment.yml --name TCP\nconda activate TCP\n```\n\n```\nexport PYTHONPATH=$PYTHONPATH:PATH_TO_TCP\n```\n\n## Dataset\n\nDownload our dataset through [Huggingface](https://huggingface.co/datasets/craigwu/tcp_carla_data) (combine the part with command `cat tcp_carla_data_part_* \u003e tcp_carla_data.zip`) or [GoogleDrive](https://drive.google.com/file/d/1HZxlSZ_wUVWkNTWMXXcSQxtYdT7GogSm/view?usp=sharing) or [BaiduYun](https://pan.baidu.com/s/11xBZwAWQ3WxQXecuuPoexQ) (提取码 8174). The total size of our dataset is around 115G, make sure you have enough space.\n\n## Training\nFirst, set the dataset path in ``TCP/config.py``.\nTraining:\n```\npython TCP/train.py --gpus NUM_OF_GPUS\n```\n\n## Data Generation\nFirst, launch the carla server,\n```\ncd CARLA_ROOT\n./CarlaUE4.sh --world-port=2000 -opengl\n```\nSet the carla path, routes file, scenario file, and data path for data generation in ``leaderboard/scripts/data_collection.sh``.\n\nStart data collection\n\n```\nsh leaderboard/scripts/data_collection.sh\n```\nAfter the data collecting process, run `tools/filter_data.py` and `tools/gen_data.py` to filter out invalid data and pack the data for training.\n\n## Evaluation\nFirst, launch the carla server,\n```\ncd CARLA_ROOT\n./CarlaUE4.sh --world-port=2000 -opengl\n```\nSet the carla path, routes file, scenario file, model ckpt, and data path for evaluation in ``leaderboard/scripts/run_evaluation.sh``.\n\nStart the evaluation\n\n```\nsh leaderboard/scripts/run_evaluation.sh\n```\n\n## Citation\n\nIf you find our repo or our paper useful, please use the following citation:\n\n```\n@inproceedings{wu2022trajectoryguided,\n title={Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline}, \n author={Penghao Wu and Xiaosong Jia and Li Chen and Junchi Yan and Hongyang Li and Yu Qiao},\n booktitle={NeurIPS},\n year={2022},\n}\n```\n\n## License\nAll code within this repository is under [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).\n\n## Acknowledgements\n\nOur code is based on several repositories:\n- [Transfuser](https://github.com/autonomousvision/transfuser)\n- [Roach](https://github.com/zhejz/carla-roach)\n- [CARLA Leaderboard](https://github.com/carla-simulator/leaderboard)\n- [Scenario Runner](https://github.com/carla-simulator/scenario_runner)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOpenDriveLab%2FTCP","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOpenDriveLab%2FTCP","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOpenDriveLab%2FTCP/lists"}