{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:39:35Z","timestamp":1777336775108,"version":"3.51.4"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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","award":["52472413"],"award-info":[{"award-number":["52472413"]}],"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":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133551","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T16:48:41Z","timestamp":1775494121000},"page":"133551","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["From multi-view images to control: End-to-end autonomous driving via scene-representation-based reinforcement learning"],"prefix":"10.1016","volume":"684","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9160-3206","authenticated-orcid":false,"given":"Jie","family":"Xia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kexu","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0096-3830","authenticated-orcid":false,"given":"Xiaodong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanbo","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boran","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.neucom.2026.133551_bib0005","doi-asserted-by":"crossref","first-page":"1364","DOI":"10.1109\/TNNLS.2020.3043505","article-title":"A survey of end-to-end driving: architectures and training methods","volume":"33","author":"Tampuu","year":"2020","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133551_bib0010","author":"Singh"},{"issue":"1","key":"10.1016\/j.neucom.2026.133551_bib0015","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."},{"issue":"12","key":"10.1016\/j.neucom.2026.133551_bib0020","doi-asserted-by":"crossref","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.2026.133551_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128423","article-title":"Recent progress, challenges and future prospects of applied deep reinforcement learning: a practical perspective in path planning","volume":"608","author":"Zhang","year":"2024","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.neucom.2026.133551_bib0030","article-title":"Data-driven traffic simulation: a comprehensive review","volume":"9","author":"Chen","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.133551_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Planning-oriented autonomous driving","author":"Hu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133551_bib0040","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","article-title":"VAD: vectorized scene representation for efficient autonomous driving","author":"Jiang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133551_bib0045","series-title":"Proceedings of the 18th European Conference on Computer Vision","article-title":"GenAD: generative end-to-end autonomous driving","author":"Zheng","year":"2024"},{"key":"10.1016\/j.neucom.2026.133551_bib0050","author":"Kingma"},{"key":"10.1016\/j.neucom.2026.133551_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131631","article-title":"Imitation learning and interactive game-based prediction-decision planning","volume":"658","author":"Wang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133551_bib0060","series-title":"Proceedings of the 2019 Global Conference for Advancement in Technology, Nagarjun College of Engineering and Tech, Bangaluru","article-title":"Covariate shift: a review and analysis on classifiers","author":"Nair","year":"2019"},{"key":"10.1016\/j.neucom.2026.133551_bib0065","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: a survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"issue":"3","key":"10.1016\/j.neucom.2026.133551_bib0070","doi-asserted-by":"crossref","first-page":"1722","DOI":"10.1109\/COMST.2020.2988367","article-title":"Deep reinforcement learning for autonomous internet of things: model, applications and challenges","volume":"22","author":"Lei","year":"2020","journal-title":"IEEE Commun. Surv. Tut."},{"key":"10.1016\/j.neucom.2026.133551_bib0075","author":"Schulman"},{"key":"10.1016\/j.neucom.2026.133551_bib0080","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","article-title":"End-to-end urban driving by imitating a reinforcement learning coach","author":"Zhang","year":"2021"},{"issue":"2","key":"10.1016\/j.neucom.2026.133551_bib0085","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1109\/TVT.2023.3312495","article-title":"Context-aware meta-RL with two-stage constrained adaptation for urban driving","volume":"73","author":"Deng","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.neucom.2026.133551_bib0090","series-title":"Proceedings of the 29th European Conference on Computer Vision","article-title":"Think2Drive: efficient reinforcement learning by thinking with (in CARLA-v2)","author":"Li","year":"2024"},{"issue":"5","key":"10.1016\/j.neucom.2026.133551_bib0095","first-page":"1","article-title":"An improved hierarchical deep reinforcement learning algorithm for multi-intelligent vehicle lane change","volume":"24","author":"Li","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.133551_bib0100","author":"Jia"},{"key":"10.1016\/j.neucom.2026.133551_bib0105","series-title":"Handbooks in Operations Research and Management Science","doi-asserted-by":"crossref","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","author":"Puterman","year":"1990"},{"key":"10.1016\/j.neucom.2026.133551_bib0110","series-title":"Reinforcement Learning: State-of-the-Art","article-title":"Partially observable markov decision processes","author":"Spaan","year":"2012"},{"issue":"3","key":"10.1016\/j.neucom.2026.133551_bib0115","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3515454","article-title":"BEVFormer: learning bird\u2019s-eye-view representation from lidar-camera via spatio-temporal transformers","volume":"47","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133551_bib0120","series-title":"Proceedings of the 30th Advances in Neural Information Processing Systems","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neucom.2026.133551_bib0125","series-title":"Proceedings of the 2022 IEEE International Conference on Multimedia and Expo","article-title":"CAT: cross attention in vision transformer","author":"Lin","year":"2022"},{"key":"10.1016\/j.neucom.2026.133551_bib0130","author":"Jiang"},{"key":"10.1016\/j.neucom.2026.133551_bib0135","author":"Cordonnier"},{"key":"10.1016\/j.neucom.2026.133551_bib0140","author":"Zhu"},{"key":"10.1016\/j.neucom.2026.133551_bib0145","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"10.1016\/j.neucom.2026.133551_bib0150","author":"Schulman"},{"key":"10.1016\/j.neucom.2026.133551_bib0155","first-page":"6119","article-title":"Trajectory-guided control prediction for end-to-end autonomous driving: a simple yet strong baseline","volume":"35","author":"Wu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133551_bib0160","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Think twice before driving: towards scalable decoders for end-to-end autonomous driving","author":"Jia","year":"2023"},{"key":"10.1016\/j.neucom.2026.133551_bib0165","author":"Li"},{"key":"10.1016\/j.neucom.2026.133551_bib0170","series-title":"Proceedings of the 12nd Advances in Neural Information Processing Systems","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"Sutton","year":"1999"},{"key":"10.1016\/j.neucom.2026.133551_bib0175","series-title":"Proceedings of the 32nd International Conference on Machine Learning","article-title":"Trust region policy optimization","author":"Schulman","year":"2015"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009483?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009483?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T23:45:43Z","timestamp":1777333543000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226009483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":35,"alternative-id":["S0925231226009483"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133551","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"From multi-view images to control: End-to-end autonomous driving via scene-representation-based reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133551","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":"133551"}}