{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:17:40Z","timestamp":1784258260980,"version":"3.55.0"},"reference-count":195,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52394264"],"award-info":[{"award-number":["52394264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission, Adminitrative Commission of Zhongguancun Science Park","doi-asserted-by":"publisher","award":["Z241100003524013"],"award-info":[{"award-number":["Z241100003524013"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["L231008"],"award-info":[{"award-number":["L231008"]}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission, Adminitrative Commission of Zhongguancun Science Park","doi-asserted-by":"publisher","award":["Z241100003524009"],"award-info":[{"award-number":["Z241100003524009"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University \u2013 Mercedes Benz Institute for Sustainable Mobility"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3495045","type":"journal-article","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T14:32:40Z","timestamp":1735569160000},"page":"11814-11834","source":"Crossref","is-referenced-by-count":22,"title":["Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2926-925X","authenticated-orcid":false,"given":"Yining","family":"Shi","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility and the State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4995-7244","authenticated-orcid":false,"given":"Kun","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility and the State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiusi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility and the State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zelin","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility and the State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junze","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility and the State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3294-6437","authenticated-orcid":false,"given":"Mengmeng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility and the State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Wang","sequence":"additional","affiliation":[{"name":"Kargobot Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0074-2448","authenticated-orcid":false,"given":"Diange","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility and the State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01790-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108796"},{"key":"ref3","article-title":"NeRF: Neural radiance field in 3D vision, a comprehensive review","author":"Gao","year":"2022","journal-title":"arXiv:2210.00379"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449912"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3333838"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827360"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02030"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01140"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01101"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00095"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref18","volume-title":"Level 5 Perception Dataset 2020","author":"Kesten et al","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref22","first-page":"1","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proc. NeurIPS Datasets Benchmarks","author":"Wilson"},{"key":"ref23","first-page":"1","article-title":"One million scenes for autonomous driving: Once dataset","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round)","author":"Mao"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802143"},{"key":"ref25","first-page":"1","article-title":"Occ3D: A large-scale 3D occupancy prediction benchmark for autonomous driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Tian"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref28","first-page":"8406","article-title":"Scene as occupancy","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Sima"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00488"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.372"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801302"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00114"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"ref36","first-page":"2148","article-title":"S3CNet: A sparse semantic scene completion network for LiDAR point clouds","volume-title":"Proc. Conf. Robot Learn.","author":"Cheng"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095302"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396092"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00867"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01915"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01401"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/107"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611261"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"ref53","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28533"},{"key":"ref55","article-title":"UniOcc: Unifying vision-centric 3D occupancy prediction with geometric and semantic rendering","author":"Pan","year":"2023","journal-title":"arXiv:2306. 09117"},{"key":"ref56","article-title":"MiLO: Multi-task learning with localization ambiguity suppression for occupancy prediction CVPR 2023 occupancy challenge report","volume-title":"arXiv:2306.11414","author":"Myeongjin","year":"2023"},{"key":"ref57","article-title":"FB-OCC: 3D occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023","journal-title":"arXiv:2307.01492"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"ref60","article-title":"PointOcc: Cylindrical tri-perspective view for point-based 3D semantic occupancy prediction","author":"Zuo","year":"2023","journal-title":"arXiv:2308.16896"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0972-7_14"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_6"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188435"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref66","first-page":"1","article-title":"EmerNeRF: Emergent spatial\u2013temporal scene decomposition via self-supervision","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00055"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref71","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref72","article-title":"RadarOcc: Robust 3D occupancy prediction with 4D imaging radar","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref73","article-title":"OccDepth: A depth-aware method for 3D semantic scene completion","author":"Miao","year":"2023","journal-title":"arXiv:2302.13540"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_5"},{"key":"ref78","first-page":"1","article-title":"OPUS: Occupancy prediction using a sparse set","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00104"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01379"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3453293"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610043"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00531"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01704"},{"key":"ref86","first-page":"7462","article-title":"Implicit neural representations with periodic activation functions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sitzmann"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160552"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02042"},{"key":"ref89","volume-title":"Occupancy Networks, Autopilot, Tesla","author":"Elluswamy","year":"2023"},{"key":"ref90","volume-title":"The CVPR 2022 Workshop Auto. Driving (WAD), IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2022"},{"key":"ref91","volume-title":"Tesla AI Day 2022","year":"2022"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref94","article-title":"Efficient and robust 2D-to-BEV representation learning via geometry-guided kernel transformer","author":"Chen","year":"2022","journal-title":"arXiv:2206.04584"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00785"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3414835"},{"key":"ref99","article-title":"M2BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation","author":"Xie","year":"2022","journal-title":"arXiv:2204.05088"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801452"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610625"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01424"},{"key":"ref103","article-title":"FlashOcc: Fast and memory-efficient occupancy prediction via channel-to-height plugin","author":"Yu","year":"2023","journal-title":"arXiv:2311.12058"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160484"},{"key":"ref105","article-title":"Spatial-temporal graph enhanced DETR towards multi-frame 3D object detection","author":"Zhang","year":"2023","journal-title":"arXiv:2307.00347"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01537"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"ref108","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00798"},{"key":"ref110","first-page":"1","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00320"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01658"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref114","article-title":"BEVerse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","author":"Zhang","year":"2022","journal-title":"arXiv:2205.09743"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_26"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00138"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_2"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01405"},{"key":"ref120","first-page":"407","article-title":"Discrete residual flow for probabilistic pedestrian behavior prediction","volume-title":"Proc. Conf. Robot Learn.","author":"Jain"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00865"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref124","article-title":"HOPE: Hierarchical spatial\u2013temporal network for occupancy flow prediction","author":"Hu","year":"2022","journal-title":"arXiv:2206.10118"},{"key":"ref125","article-title":"VectorFlow: Combining images and vectors for traffic occupancy and flow prediction","author":"Huang","year":"2022","journal-title":"arXiv:2208.04530"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160855"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref128","article-title":"Copilot4D: Learning unsupervised world models for autonomous driving via discrete diffusion","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00110"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01304"},{"key":"ref136","article-title":"SPOT: Scalable 3D pre-training via occupancy prediction for learning transferable 3D representations","author":"Yan","year":"2023","journal-title":"arXiv:2309.10527"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28141"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00335"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01293"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3362635"},{"key":"ref142","article-title":"UniWorld: Autonomous driving pre-training via world models","author":"Min","year":"2023","journal-title":"arXiv:2308.07234"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01470"},{"key":"ref144","first-page":"539","article-title":"Surrounddepth: Entangling surrounding views for self-supervised multi-camera depth estimation","volume-title":"Proc. Conf. Robot Learn.","author":"Wei"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00876"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00861"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00133"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref149","article-title":"OccNeRF: Self-supervised multi-camera occupancy prediction with neural radiance fields","author":"Zhang","year":"2023","journal-title":"arXiv:2312.09243"},{"key":"ref150","article-title":"OccFlowNet: Towards self-supervised occupancy estimation via differentiable rendering and occupancy flow","author":"Boeder","year":"2024","journal-title":"arXiv:2402.12792"},{"key":"ref151","article-title":"Let Occ flow: Self-supervised 3D occupancy flow prediction","volume-title":"Proc. Conf. Robot Learn.","author":"Liu"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01373"},{"key":"ref153","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref154","article-title":"OVO: Open-vocabulary occupancy","author":"Tan","year":"2023","journal-title":"arXiv:2305.16133"},{"key":"ref155","first-page":"1","article-title":"POP-3D: Open-vocabulary 3D occupancy prediction from images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Vobecky"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.3390\/app122311982"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912067"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20258"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610648"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CASE56687.2023.10260358"},{"key":"ref164","article-title":"PLUTO: Pushing the limit of imitation learning-based planning for autonomous driving","author":"Cheng","year":"2024","journal-title":"arXiv:2404.14327"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236586"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3044909"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.20485\/jsaeijae.7.AVEC14_53"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref169","article-title":"Imitation with spatial\u2013temporal heatmap: 2nd place solution for NuPlan challenge","author":"Hu","year":"2023","journal-title":"arXiv:2306.15700"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422055"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3304530"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636480"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3296209"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_27"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref181","article-title":"GAIA-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv:2309.17080"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"ref185","article-title":"Urban scene diffusion through semantic occupancy map","author":"Zhang","year":"2024","journal-title":"arXiv:2403.11697"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02677"},{"key":"ref187","first-page":"20703","article-title":"Model-based imitation learning for urban driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hu"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968560"},{"key":"ref190","volume-title":"LightwheelOcc: A 3D Occupancy Synthetic Dataset in Autonomous Driving","author":"LightwheelAI","year":"2024"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"ref192","volume-title":"Video Generation Models as World Simulators","author":"Contributors","year":"2024"},{"key":"ref193","article-title":"OccSora: 4D occupancy generation models as world simulators for autonomous driving","author":"Wang","year":"2024","journal-title":"arXiv:2405.20337"},{"key":"ref194","first-page":"1","article-title":"Good: Exploring geometric cues for detecting objects in an open world","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Huang"},{"key":"ref195","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","volume":"1","author":"Shi"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10817778.pdf?arnumber=10817778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:48:55Z","timestamp":1752169735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":195,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3495045","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}