{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:35:59Z","timestamp":1782833759682,"version":"3.54.5"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373325"],"award-info":[{"award-number":["62373325"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6190334"],"award-info":[{"award-number":["6190334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY21F030016"],"award-info":[{"award-number":["LY21F030016"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["No.300102343503"],"award-info":[{"award-number":["No.300102343503"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s10489-024-05478-y","type":"journal-article","created":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T05:01:32Z","timestamp":1715576492000},"page":"6400-6414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Graph-based multi agent reinforcement learning for on-ramp merging in mixed traffic"],"prefix":"10.1007","volume":"54","author":[{"given":"Dongwei","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingwei","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baojie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"issue":"2","key":"5478_CR1","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1109\/TIV.2022.3223131","volume":"8","author":"L Chen","year":"2022","unstructured":"Chen L, Li Y, Huang C, Li B, Xing Y, Tian D, Li L, Hu Z, Na X, Li Z et al (2022) Milestones in autonomous driving and intelligent vehicles: survey of surveys. IEEE Trans Intell Vehicles 8(2):1046\u20131056","journal-title":"IEEE Trans Intell Vehicles"},{"issue":"10","key":"5478_CR2","doi-asserted-by":"publisher","first-page":"7572","DOI":"10.1109\/JIOT.2021.3130054","volume":"9","author":"C Gao","year":"2021","unstructured":"Gao C, Wang G, Shi W, Wang Z, Chen Y (2021) Autonomous driving security: state of the art and challenges. IEEE Internet Things J 9(10):7572\u20137595","journal-title":"IEEE Internet Things J"},{"key":"5478_CR3","doi-asserted-by":"crossref","unstructured":"Qiu W, Ting Q, Shuyou Y, Hongyan G, Hong C (2015) Autonomous vehicle longitudinal following control based on model predictive control. In: 2015 34th Chinese Control Conference (CCC), IEEE, pp 8126\u20138131","DOI":"10.1109\/ChiCC.2015.7260933"},{"issue":"6","key":"5478_CR4","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.3390\/s17061244","volume":"17","author":"G Han","year":"2017","unstructured":"Han G, Fu W, Wang W, Wu Z (2017) The lateral tracking control for the intelligent vehicle based on adaptive pid neural network. Sensors 17(6):1244","journal-title":"Sensors"},{"key":"5478_CR5","doi-asserted-by":"crossref","unstructured":"Hosseinzadeh M, Sinopoli B, Kolmanovsky I, Baruah S (2022) Implementing optimization-based control tasks in cyber-physical systems with limited computing capacity. In: 2022 2nd International workshop on computation-aware algorithmic design for cyber-physical systems (CAADCPS), IEEE pp 15\u201316","DOI":"10.1109\/CAADCPS56132.2022.00009"},{"issue":"6","key":"5478_CR6","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2021","unstructured":"Kiran BR, Sobh I, Talpaert V, Mannion P, Al Sallab AA, Yogamani S, P\u00e9rez P (2021) Deep reinforcement learning for autonomous driving: a survey. IEEE Trans Intell Transp Syst 23(6):4909\u20134926","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"1","key":"5478_CR7","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s10489-020-01827-9","volume":"51","author":"D-H Lee","year":"2021","unstructured":"Lee D-H, Chen K-L, Liou K-H, Liu C-L, Liu J-L (2021) Deep learning and control algorithms of direct perception for autonomous driving. Appl Intell 51(1):237\u2013247","journal-title":"Appl Intell"},{"key":"5478_CR8","doi-asserted-by":"crossref","unstructured":"Nakka SKS, Chalaki B, Malikopoulos AA (2022) A multi-agent deep reinforcement learning coordination framework for connected and automated vehicles at merging roadways. In: 2022 American Control Conference (ACC), IEEE, pp 3297\u20133302","DOI":"10.23919\/ACC53348.2022.9867314"},{"issue":"7","key":"5478_CR9","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1111\/mice.12702","volume":"36","author":"S Chen","year":"2021","unstructured":"Chen S, Dong J, Ha P, Li Y, Labi S (2021) Graph neural network and reinforcement learning for multi-agent cooperative control of connected autonomous vehicles. Comput Aided Civ Infrastruct Eng 36(7):838\u2013857","journal-title":"Comput Aided Civ Infrastruct Eng"},{"key":"5478_CR10","unstructured":"Zhou M, Luo J, Villella J, Yang Y, Rusu D, Miao J, Zhang W, Alban M, Fadakar I, Chen Z et al (2020) Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving. arXiv:2010.09776"},{"issue":"8","key":"5478_CR11","doi-asserted-by":"publisher","first-page":"9261","DOI":"10.1007\/s10489-022-03924-3","volume":"53","author":"H Wang","year":"2023","unstructured":"Wang H, Xie X, Zhou L (2023) Transform networks for cooperative multi-agent deep reinforcement learning. Appl Intell 53(8):9261\u20139269","journal-title":"Appl Intell"},{"key":"5478_CR12","doi-asserted-by":"crossref","unstructured":"Munikoti S, Agarwal D, Das L, Halappanavar M, Natarajan B (2022) Challenges and opportunities in deep reinforcement learning with graph neural networks: a comprehensive review of algorithms and applications. arXiv:2206.07922","DOI":"10.1109\/TNNLS.2023.3283523"},{"issue":"11","key":"5478_CR13","doi-asserted-by":"publisher","first-page":"12801","DOI":"10.1007\/s10489-021-03120-9","volume":"52","author":"D Singh","year":"2022","unstructured":"Singh D, Srivastava R (2022) Graph neural network with rnns based trajectory prediction of dynamic agents for autonomous vehicle. Appl Intell 52(11):12801\u201312816","journal-title":"Appl Intell"},{"key":"5478_CR14","doi-asserted-by":"crossref","unstructured":"Kendall A, Hawke J, Janz D, Mazur P, Reda D, Allen J-M, Lam V-D, Bewley A, Shah A (2019) Learning to drive in a day. In: 2019 International conference on robotics and automation (ICRA), IEEE, pp 8248\u20138254","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"5478_CR15","doi-asserted-by":"crossref","unstructured":"Chen J, Yuan B, Tomizuka M (2019) Model-free deep reinforcement learning for urban autonomous driving. In: 2019 IEEE Intelligent transportation systems conference (ITSC), IEEE, pp 2765\u20132771","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"5478_CR16","doi-asserted-by":"crossref","unstructured":"Yan Z, Kreidieh AR, Vinitsky E, Bayen AM, Wu C (2022) Unified automatic control of vehicular systems with reinforcement learning. IEEE Trans Autom Sci Eng","DOI":"10.1109\/TASE.2022.3168621"},{"issue":"1","key":"5478_CR17","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s43684-022-00045-z","volume":"2","author":"J Dinneweth","year":"2022","unstructured":"Dinneweth J, Boubezoul A, Mandiau R, Espi\u00e9 S (2022) Multi-agent reinforcement learning for autonomous vehicles: a survey. Autonomous Intell Syst 2(1):27","journal-title":"Autonomous Intell Syst"},{"key":"5478_CR18","doi-asserted-by":"crossref","unstructured":"Yin Q, Yu T, Shen S, Yang J, Zhao M, Ni W, Huang K, Liang B, Wang L (2024) Distributed deep reinforcement learning: a survey and a multi-player multi-agent learning toolbox. Mach Intell Res 1\u201320","DOI":"10.1007\/s11633-023-1454-4"},{"issue":"1","key":"5478_CR19","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s43684-022-00023-5","volume":"2","author":"W Zhou","year":"2022","unstructured":"Zhou W, Chen D, Yan J, Li Z, Yin H, Ge W (2022) Multi-agent reinforcement learning for cooperative lane changing of connected and autonomous vehicles in mixed traffic. Autonomous Intell Syst 2(1):5","journal-title":"Autonomous Intell Syst"},{"key":"5478_CR20","doi-asserted-by":"crossref","unstructured":"Bhalla S, Ganapathi\u00a0Subramanian S, Crowley M (2020) Deep multi agent reinforcement learning for autonomous driving. In: Advances in Artificial Intelligence: 33rd Canadian Conference on Artificial Intelligence, Canadian AI 2020, Ottawa, ON, Canada, May 13\u201315, 2020, Proceedings, Springer, pp 67\u201378","DOI":"10.1007\/978-3-030-47358-7_7"},{"key":"5478_CR21","doi-asserted-by":"crossref","unstructured":"Palanisamy P (2020). Multi-agent connected autonomous driving using deep reinforcement learning. In: 2020 International joint conference on neural networks (IJCNN), IEEE, pp 1\u20137","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"issue":"4","key":"5478_CR22","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/s10015-023-00912-9","volume":"28","author":"Z Han","year":"2023","unstructured":"Han Z, Liang Y, Ohkura K (2023) Developing multi-agent adversarial environment using reinforcement learning and imitation learning. Artif Life Robot 28(4):703\u2013709","journal-title":"Artif Life Robot"},{"issue":"11","key":"5478_CR23","doi-asserted-by":"publisher","first-page":"4948","DOI":"10.3390\/app11114948","volume":"11","author":"L Canese","year":"2021","unstructured":"Canese L, Cardarilli GC, Di Nunzio L, Fazzolari R, Giardino D, Re M, Span\u00f2 S (2021) Multi-agent reinforcement learning: a review of challenges and applications. Appl Sci 11(11):4948","journal-title":"Appl Sci"},{"issue":"12","key":"5478_CR24","doi-asserted-by":"publisher","first-page":"9190","DOI":"10.1109\/JIOT.2021.3093523","volume":"9","author":"L Ye","year":"2021","unstructured":"Ye L, Wang Z, Chen X, Wang J, Wu K, Lu K (2021) Gsan: Graph self-attention network for learning spatial-temporal interaction representation in autonomous driving. IEEE Internet Things J 9(12):9190\u20139204","journal-title":"IEEE Internet Things J"},{"key":"5478_CR25","unstructured":"Wang J, Shi T, Wu Y, Miranda-Moreno L, Sun L (2020) Multi-agent graph reinforcement learning for connected automated driving. In: Proceedings of the 37th international conference on machine learning (ICML), pp 1\u20136"},{"key":"5478_CR26","doi-asserted-by":"publisher","first-page":"128172","DOI":"10.1016\/j.physa.2022.128172","volume":"607","author":"S Wang","year":"2022","unstructured":"Wang S, Fujii H, Yoshimura S (2022) Generating merging strategies for connected autonomous vehicles based on spatiotemporal information extraction module and deep reinforcement learning. Phys A Stat Mech Appl 607:128172","journal-title":"Phys A Stat Mech Appl"},{"key":"5478_CR27","doi-asserted-by":"publisher","first-page":"102505","DOI":"10.1016\/j.sysarc.2022.102505","volume":"126","author":"Y Peng","year":"2022","unstructured":"Peng Y, Tan G, Si H, Li J (2022) Drl-gat-sa: Deep reinforcement learning for autonomous driving planning based on graph attention networks and simplex architecture. J Syst Archit 126:102505","journal-title":"J Syst Archit"},{"key":"5478_CR28","doi-asserted-by":"crossref","unstructured":"Zhu J, Easa S, Gao K (2022) Merging control strategies of connected and autonomous vehicles at freeway on-ramps: a comprehensive review. J Intell Connect Veh 5(2):99\u2013111","DOI":"10.1108\/JICV-02-2022-0005"},{"key":"5478_CR29","doi-asserted-by":"crossref","unstructured":"Wang P, Chan C-Y (2017) Formulation of deep reinforcement learning architecture toward autonomous driving for on-ramp merge. In: 2017 IEEE 20th International conference on intelligent transportation systems (ITSC), IEEE, pp 1\u20136","DOI":"10.1109\/ITSC.2017.8317735"},{"issue":"10","key":"5478_CR30","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1177\/0361198120935873","volume":"2674","author":"T Ren","year":"2020","unstructured":"Ren T, Xie Y, Jiang L (2020) Cooperative highway work zone merge control based on reinforcement learning in a connected and automated environment. Transp Res Rec 2674(10):363\u2013374","journal-title":"Transp Res Rec"},{"key":"5478_CR31","doi-asserted-by":"crossref","unstructured":"Schester L, Ortiz LE (2021) Automated driving highway traffic merging using deep multi-agent reinforcement learning in continuous state-action spaces. In: 2021 IEEE Intelligent vehicles symposium (IV), IEEE, pp. 280\u2013287","DOI":"10.1109\/IV48863.2021.9575676"},{"key":"5478_CR32","doi-asserted-by":"publisher","unstructured":"He C, Sun D, Zhao M, Zhao H (2021) Cooperative group control strategy in the on-ramp area for connected and automated vehicles under mixed traffic environment. In: 2021 China Automation Congress (CAC), pp 7943\u20137948. https:\/\/doi.org\/10.1109\/CAC53003.2021.9728034","DOI":"10.1109\/CAC53003.2021.9728034"},{"key":"5478_CR33","doi-asserted-by":"crossref","unstructured":"Chen D, Hajidavalloo MR, Li Z, Chen K, Wang Y, Jiang L, Wang Y (2023) Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic. IEEE Trans Intell Transp Syst","DOI":"10.1109\/TITS.2023.3285442"},{"key":"5478_CR34","unstructured":"Krajzewicz D, Hertkorn G, R\u00f6ssel C, Wagner P (2002) Sumo (simulation of urban mobility)-an open-source traffic simulation. In: Proceedings of the 4th Middle East symposium on simulation and modelling (MESM20002), pp 183\u2013187"},{"key":"5478_CR35","doi-asserted-by":"crossref","unstructured":"Bellman R (1957) A markovian decision process. J Math Mech 679\u2013684","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"5478_CR36","unstructured":"Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555"},{"key":"5478_CR37","doi-asserted-by":"crossref","unstructured":"Jia J, Xing X, Chang DE (2022) Gru-attention based td3 network for mobile robot navigation. In: 2022 22nd International conference on control, automation and systems (ICCAS), IEEE, pp 1642\u20131647","DOI":"10.23919\/ICCAS55662.2022.10003950"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05478-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05478-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05478-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,15]],"date-time":"2024-06-15T12:15:26Z","timestamp":1718453726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05478-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":37,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["5478"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05478-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]},"assertion":[{"value":"18 April 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}