{"url":"/task/autonomous-vehicles","name":"Autonomous Vehicles","slug":"autonomous-vehicles","description_markdown":"Autonomous vehicles is the task of making a vehicle that can guide itself without human conduction.\r\n\r\nMany of the state-of-the-art results can be found at more general task pages such as [3D Object Detection](https://paperswithcode.com/task/3d-object-detection) and [Semantic Segmentation](https://paperswithcode.com/task/semantic-segmentation).\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision](https://arxiv.org/abs/2007.13124) )</span>","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2605,"papers_with_code":695,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":29,"subtasks":15,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/autonomous-vehicles-on-apollocar3d","slug":"autonomous-vehicles-on-apollocar3d","dataset":"ApolloCar3D","dataset_url":"/dataset/apollocar3d","rows_in_archive":2,"metrics":["A3DP"],"first_row_in_archive_order":{"model":"BAAM","paper_title":"BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling","paper_url":"/paper/baam-monocular-3d-pose-and-shape","paper_date":"2023-01-01","arxiv_id":null,"code_links":[{"title":"gywns6287/baam","url":"https://github.com/gywns6287/baam"}],"syntology":null}}],"datasets":[{"url":"/dataset/carla","name":"CARLA","full_name":"Car Learning to Act","num_papers_in_archive":1345},{"url":"/dataset/airsim","name":"AirSim","full_name":"","num_papers_in_archive":285},{"url":"/dataset/interaction-dataset","name":"INTERACTION Dataset","full_name":"","num_papers_in_archive":81},{"url":"/dataset/talk2car","name":"Talk2Car","full_name":"","num_papers_in_archive":45},{"url":"/dataset/argoverse-2-motion-forecasting","name":"Argoverse 2 Motion Forecasting","full_name":"","num_papers_in_archive":39},{"url":"/dataset/radarscenes","name":"RadarScenes","full_name":"","num_papers_in_archive":27},{"url":"/dataset/road","name":"ROAD","full_name":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","num_papers_in_archive":27},{"url":"/dataset/drive-act","name":"Drive&Act","full_name":"","num_papers_in_archive":26},{"url":"/dataset/apollocar3d","name":"ApolloCar3D","full_name":"","num_papers_in_archive":17},{"url":"/dataset/dada-2000","name":"DADA-2000","full_name":"","num_papers_in_archive":16},{"url":"/dataset/titan","name":"TITAN","full_name":"","num_papers_in_archive":15},{"url":"/dataset/presil","name":"PreSIL","full_name":"Precise Synthetic Image and LiDAR","num_papers_in_archive":13},{"url":"/dataset/comma-2k19","name":"comma 2k19","full_name":"","num_papers_in_archive":11},{"url":"/dataset/synthcity","name":"SynthCity","full_name":"","num_papers_in_archive":8},{"url":"/dataset/ford-av-dataset","name":"Ford AV Dataset","full_name":"","num_papers_in_archive":7},{"url":"/dataset/lyft-level-5-prediction","name":"Lyft Level 5 Prediction","full_name":"","num_papers_in_archive":7},{"url":"/dataset/eurocity-persons","name":"EuroCity Persons","full_name":"","num_papers_in_archive":6},{"url":"/dataset/tcg","name":"TCG","full_name":"Traffic Control Gesture","num_papers_in_archive":4},{"url":"/dataset/vci-dut","name":"CITR & DUT","full_name":"CITR dataset and DUT dataset","num_papers_in_archive":3},{"url":"/dataset/hsd","name":"HSD","full_name":"Honda Scenes Dataset","num_papers_in_archive":3},{"url":"/dataset/tusimple-lane","name":"TuSimple Lane","full_name":"","num_papers_in_archive":3},{"url":"/dataset/eyecar","name":"EyeCar","full_name":"","num_papers_in_archive":2},{"url":"/dataset/citr-dataset","name":"CITR Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/in2laama","name":"IN2LAAMA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mvx","name":"MVX","full_name":"Multimodal V2X","num_papers_in_archive":1},{"url":"/dataset/panoramic-video-panoptic-segmentation-dataset","name":"Panoramic Video Panoptic Segmentation Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/precog","name":"PRECOG","full_name":"PREdiction of Clinical Outcomes from Genomic Profiles","num_papers_in_archive":1},{"url":"/dataset/car-datasets-in-multiple-scenes","name":"Car datasets in multiple scenes","full_name":"","num_papers_in_archive":0},{"url":"/dataset/hyper-drive","name":"Hyper Drive","full_name":"Hyperspectral Driving Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-car-instance-understanding","name":"3D Car Instance Understanding"},{"url":"/task/autonomous-driving","name":"Autonomous Driving"},{"url":"/task/autonomous-navigation","name":"Autonomous Navigation"},{"url":"/task/carla-leaderboard-2-0","name":"CARLA Leaderboard 2.0"},{"url":"/task/driver-attention-monitoring","name":"Driver Attention Monitoring"},{"url":"/task/fast-vehicle-detection","name":"Fast Vehicle Detection"},{"url":"/task/lane-detection","name":"Lane Detection"},{"url":"/task/loop-closure-detection","name":"Loop Closure Detection"},{"url":"/task/pedestrian-attribute-recognition","name":"Pedestrian Attribute Recognition"},{"url":"/task/pedestrian-density-estimation","name":"Pedestrian Density Estimation"},{"url":"/task/pedestrian-detection","name":"Pedestrian Detection"},{"url":"/task/self-driving-cars","name":"Self-Driving Cars"},{"url":"/task/simultaneous-localization-and-mapping","name":"Simultaneous Localization and Mapping"},{"url":"/task/traffic-sign-recognition","name":"Traffic Sign Recognition"},{"url":"/task/traffic-signal-control","name":"Traffic Signal Control"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":695,"tagged_in_all":2605,"items":[{"url":"/paper/airsim-high-fidelity-visual-and-physical","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","date":"2017-05-15","arxiv_id":"1705.05065","repositories_listed":25,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":7}},{"url":"/paper/split-computing-and-early-exiting-for-deep","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","date":"2021-03-08","arxiv_id":"2103.04505","repositories_listed":19,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/nuscenes-a-multimodal-dataset-for-autonomous","title":"nuScenes: A multimodal dataset for autonomous driving","date":"2019-03-26","arxiv_id":"1903.11027","repositories_listed":16,"syntology":{"n":17,"n_ran":1,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/flow-architecture-and-benchmarking-for","title":"Flow: A Modular Learning Framework for Mixed Autonomy Traffic","date":"2017-10-16","arxiv_id":"1710.05465","repositories_listed":16,"syntology":{"n":17,"n_ran":1,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/deep-dual-resolution-networks-for-real-time","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","date":"2021-01-15","arxiv_id":"2101.06085","repositories_listed":8,"syntology":null},{"url":"/paper/leaf-a-benchmark-for-federated-settings","title":"LEAF: A Benchmark for Federated Settings","date":"2018-12-03","arxiv_id":"1812.01097","repositories_listed":7,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/dynaslam-tracking-mapping-and-inpainting-in","title":"DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes","date":"2018-06-14","arxiv_id":"1806.05620","repositories_listed":7,"syntology":null},{"url":"/paper/counterfactual-multi-agent-policy-gradients","title":"Counterfactual Multi-Agent Policy Gradients","date":"2017-05-24","arxiv_id":"1705.08926","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/scalable-scene-flow-from-point-clouds-in-the","title":"Scalable Scene Flow from Point Clouds in the Real World","date":"2021-03-01","arxiv_id":"2103.01306","repositories_listed":5,"syntology":null},{"url":"/paper/lidar-camera-calibration-using-3d-3d-point","title":"LiDAR-Camera Calibration using 3D-3D Point correspondences","date":"2017-05-27","arxiv_id":"1705.09785","repositories_listed":5,"syntology":null},{"url":"/paper/gaussian-yolov3-an-accurate-and-fast-object","title":"Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving","date":"2019-04-09","arxiv_id":"1904.04620","repositories_listed":4,"syntology":null},{"url":"/paper/formal-security-analysis-of-neural-networks","title":"Formal Security Analysis of Neural Networks using Symbolic Intervals","date":"2018-04-28","arxiv_id":"1804.10829","repositories_listed":4,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/on-the-importance-of-stereo-for-accurate","title":"On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach","date":"2018-03-26","arxiv_id":"1803.09719","repositories_listed":4,"syntology":null},{"url":"/paper/joint-3d-proposal-generation-and-object","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","date":"2017-12-06","arxiv_id":"1712.02294","repositories_listed":4,"syntology":null},{"url":"/paper/tumtraf-v2x-cooperative-perception-dataset","title":"TUMTraf V2X Cooperative Perception Dataset","date":"2024-03-02","arxiv_id":"2403.01316","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/trajdata-a-unified-interface-to-multiple-1","title":"trajdata: A Unified Interface to Multiple Human Trajectory Datasets","date":"2023-07-26","arxiv_id":"2307.13924","repositories_listed":3,"syntology":null},{"url":"/paper/trafficbots-towards-world-models-for","title":"TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction","date":"2023-03-07","arxiv_id":"2303.04116","repositories_listed":3,"syntology":null},{"url":"/paper/flowlens-seeing-beyond-the-fov-via-flow","title":"Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer","date":"2022-11-21","arxiv_id":"2211.11293","repositories_listed":3,"syntology":null},{"url":"/paper/aimotive-dataset-a-multimodal-dataset-for","title":"aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range Perception","date":"2022-11-17","arxiv_id":"2211.09445","repositories_listed":3,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/deep-multi-agent-reinforcement-learning-for-2","title":"Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic","date":"2021-05-12","arxiv_id":"2105.05701","repositories_listed":3,"syntology":null},{"url":"/paper/multimodal-object-detection-via-bayesian","title":"Multimodal Object Detection via Probabilistic Ensembling","date":"2021-04-07","arxiv_id":"2104.02904","repositories_listed":3,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/trafficqa-a-question-answering-benchmark-and","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","date":"2021-03-29","arxiv_id":"2103.15538","repositories_listed":3,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":2}},{"url":"/paper/road-the-road-event-awareness-dataset-for","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","date":"2021-02-23","arxiv_id":"2102.11585","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/centerfusion-center-based-radar-and-camera","title":"CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection","date":"2020-11-10","arxiv_id":"2011.04841","repositories_listed":3,"syntology":null},{"url":"/paper/keep-your-eyes-on-the-lane-attention-guided","title":"Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection","date":"2020-10-22","arxiv_id":"2010.12035","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/accelerating-3d-deep-learning-with-pytorch3d","title":"Accelerating 3D Deep Learning with PyTorch3D","date":"2020-07-16","arxiv_id":"2007.08501","repositories_listed":3,"syntology":null},{"url":"/paper/avp-slam-semantic-visual-mapping-and","title":"AVP-SLAM: Semantic Visual Mapping and Localization for Autonomous Vehicles in the Parking Lot","date":"2020-07-03","arxiv_id":"2007.01813","repositories_listed":3,"syntology":null},{"url":"/paper/one-thousand-and-one-hours-self-driving","title":"One Thousand and One Hours: Self-driving Motion Prediction Dataset","date":"2020-06-25","arxiv_id":"2006.14480","repositories_listed":3,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/social-stgcnn-a-social-spatio-temporal-graph","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","date":"2020-02-27","arxiv_id":"2002.11927","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/argoverse-3d-tracking-and-forecasting-with-1","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","date":"2019-11-06","arxiv_id":"1911.02620","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":2,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}