{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T12:14:44Z","timestamp":1783685684590,"version":"3.55.0"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134411","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:51:29Z","timestamp":1783353089000},"page":"134411","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["BEV representation prediction via a world model with cross-entropy data aggregation"],"prefix":"10.1016","volume":"700","author":[{"given":"Jiatong","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaheng","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2505-2394","authenticated-orcid":false,"given":"Yue","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanjian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3133-8031","authenticated-orcid":false,"given":"Yanjun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134411_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129857","article-title":"Multi-modal information fusion for multi-task end-to-end behavior prediction in autonomous driving","volume":"634","author":"Baicang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134411_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14403","article-title":"MP3: a unified model to map, perceive, predict and plan","author":"Casas","year":"2021"},{"key":"10.1016\/j.neucom.2026.134411_bib0015","doi-asserted-by":"crossref","first-page":"10164","DOI":"10.1109\/TPAMI.2024.3435937","article-title":"End-to-end autonomous driving: challenges and frontiers","volume":"46","author":"Chen","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134411_bib0020","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/TIV.2023.3318070","article-title":"Recent advancements in end-to-end autonomous driving using deep learning: a survey","volume":"9","author":"Chib","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134411_bib0025","series-title":"Conference on Robot Learning","first-page":"1","article-title":"CARLA: an open urban driving simulator","author":"Dosovitskiy","year":"2017"},{"key":"10.1016\/j.neucom.2026.134411_bib0030","doi-asserted-by":"crossref","first-page":"2983","DOI":"10.1109\/TMECH.2024.3402126","article-title":"Evolutionary end-to-end autonomous driving model with continuous-time neural networks","volume":"29","author":"Du","year":"2024","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"10.1016\/j.neucom.2026.134411_bib0035","first-page":"1","article-title":"World models for autonomous driving: an initial survey","author":"Guan","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134411_bib0040","author":"Hafner"},{"key":"10.1016\/j.neucom.2026.134411_bib0045","series-title":"International Conference on Machine Learning","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"Hafner","year":"2019"},{"key":"10.1016\/j.neucom.2026.134411_bib0050","author":"Hafner"},{"key":"10.1016\/j.neucom.2026.134411_bib0055","first-page":"1","article-title":"Mastering diverse control tasks through world models","author":"Hafner","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.neucom.2026.134411_bib0060","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"251","article-title":"Urban driving with conditional imitation learning","author":"Hawke","year":"2020"},{"key":"10.1016\/j.neucom.2026.134411_bib0065","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134411_bib0070","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/s42154-023-00256-x","article-title":"Towards safe autonomous driving: decision making with observation-robust reinforcement learning","volume":"6","author":"He","year":"2023","journal-title":"Automot. Innov."},{"key":"10.1016\/j.neucom.2026.134411_bib0075","first-page":"1","article-title":"Double deep Q-Networks based game-theoretic equilibrium control of automated vehicles at autonomous intersection","author":"Hu","year":"2024","journal-title":"Automot. Innov."},{"key":"10.1016\/j.neucom.2026.134411_bib0080","series-title":"European Conference on Computer Vision","first-page":"533","article-title":"St-p3: end-to-end vision-based autonomous driving via spatial-temporal feature learning","author":"Hu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134411_bib0085","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17853","article-title":"Planning-oriented autonomous driving","author":"Hu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134411_bib0090","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TIV.2022.3167103","article-title":"A survey on trajectory-prediction methods for autonomous driving","volume":"7","author":"Huang","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134411_bib0095","author":"Karras"},{"key":"10.1016\/j.neucom.2026.134411_bib0100","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12697","article-title":"Pointpillars: fast encoders for object detection from point clouds","author":"Lang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134411_bib0105","doi-asserted-by":"crossref","first-page":"2151","DOI":"10.1109\/TPAMI.2023.3333838","article-title":"Delving into the devils of bird\u2019s-eye-view perception: a review, evaluation and recipe","volume":"46","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134411_bib0110","series-title":"European Conference on Computer Vision","first-page":"142","article-title":"Think2Drive: efficient reinforcement learning by thinking with latent world model for autonomous driving (in CARLA-V2)","author":"Li","year":"2025"},{"key":"10.1016\/j.neucom.2026.134411_bib0115","series-title":"2022 International Conference on Robotics and Automation (ICRA)","first-page":"4628","article-title":"Hdmapnet: an online hd map construction and evaluation framework","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134411_bib0120","doi-asserted-by":"crossref","first-page":"18442","DOI":"10.52202\/068431-1340","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume":"35","author":"Li","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134411_bib0125","doi-asserted-by":"crossref","first-page":"10421","DOI":"10.52202\/068431-0757","article-title":"Bevfusion: a simple and robust LiDAR-camera fusion framework","volume":"35","author":"Liang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134411_bib0130","author":"Pan"},{"key":"10.1016\/j.neucom.2026.134411_bib0135","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127874","article-title":"Autonomous driving in traffic with end-to-end vision-based deep learning","volume":"594","author":"Paniego","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134411_bib0140","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"5935","article-title":"Bevsegformer: bird\u2019s eye view semantic segmentation from arbitrary camera rigs","author":"Peng","year":"2023"},{"key":"10.1016\/j.neucom.2026.134411_bib0145","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16","first-page":"194","article-title":"Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D","author":"Philion","year":"2020"},{"key":"10.1016\/j.neucom.2026.134411_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11763","article-title":"Exploring data aggregation in policy learning for vision-based urban autonomous driving","author":"Prakash","year":"2020"},{"key":"10.1016\/j.neucom.2026.134411_bib0155","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8555","article-title":"Categorical depth distribution network for monocular 3D object detection","author":"Reading","year":"2021"},{"key":"10.1016\/j.neucom.2026.134411_bib0160","author":"Roddick"},{"key":"10.1016\/j.neucom.2026.134411_bib0165","series-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"Ross","year":"2011"},{"key":"10.1016\/j.neucom.2026.134411_bib0170","author":"Sallab"},{"key":"10.1016\/j.neucom.2026.134411_bib0175","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8406","article-title":"Scene as occupancy","author":"Tong","year":"2023"},{"key":"10.1016\/j.neucom.2026.134411_bib0180","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134411_bib0185","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14749","article-title":"Driving into the future: multiview visual forecasting and planning with world model for autonomous driving","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134411_bib0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102671","article-title":"A survey on occupancy perception for autonomous driving: the information fusion perspective","volume":"114","author":"Xu","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134411_bib0195","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Query-efficient imitation learning for end-to-end simulated driving","author":"Zhang","year":"2017"},{"key":"10.1016\/j.neucom.2026.134411_bib0200","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15222","article-title":"End-to-end urban driving by imitating a reinforcement learning coach","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134411_bib0205","series-title":"European Conference on Computer Vision","first-page":"55","article-title":"Occworld: learning a 3D occupancy world model for autonomous driving","author":"Zheng","year":"2024"},{"key":"10.1016\/j.neucom.2026.134411_bib0210","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4490","article-title":"Voxelnet: end-to-end learning for point cloud based 3D object detection","author":"Zhou","year":"2018"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018096?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018096?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T11:24:40Z","timestamp":1783682680000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226018096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":42,"alternative-id":["S0925231226018096"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134411","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"BEV representation prediction via a world model with cross-entropy data aggregation","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134411","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134411"}}