{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:42:56Z","timestamp":1779334976805,"version":"3.51.4"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Natural Science Foundation of China under Grant","award":["61825305"],"award-info":[{"award-number":["61825305"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s10489-022-04086-y","type":"journal-article","created":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T06:03:11Z","timestamp":1664604191000},"page":"12736-12748","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Kernel-based multiagent reinforcement learning for near-optimal formation control of mobile robots"],"prefix":"10.1007","volume":"53","author":[{"given":"Ronghua","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinglong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingwen","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaoqian","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,1]]},"reference":[{"key":"4086_CR1","unstructured":"Zhao W, Liu H, Lewis FL, Wang X (2021) Data-driven optimal formation control for quadrotor team with unknown dynamics. IEEE Trans Cybern, 1\u201310"},{"key":"4086_CR2","doi-asserted-by":"crossref","unstructured":"Wang D, Wei W, Wang X, Gao Y, Li Y, Yu Q, Fan Z (2021) Formation control of multiple mecanum-wheeled mobile robots with physical constraints and uncertainties. Appl Intell, 1\u201320","DOI":"10.1007\/s10489-021-02459-3"},{"issue":"7","key":"4086_CR3","doi-asserted-by":"publisher","first-page":"4664","DOI":"10.1007\/s10489-020-02104-5","volume":"51","author":"H Liang","year":"2021","unstructured":"Liang H, Fu Y, Gao J (2021) Bio-inspired self-organized cooperative control consensus for crowded UUV swarm based on adaptive dynamic interaction topology. Appl Intell 51(7):4664\u20134681","journal-title":"Appl Intell"},{"issue":"12","key":"4086_CR4","doi-asserted-by":"publisher","first-page":"5468","DOI":"10.1109\/TNNLS.2021.3068762","volume":"32","author":"Y Zhao","year":"2021","unstructured":"Zhao Y, Ma Y, Hu S (2021) USV formation and path-following control via deep reinforcement learning with random braking. IEEE Trans Neural Netw Learn Syst 32(12):5468\u20135478","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4086_CR5","doi-asserted-by":"crossref","unstructured":"Chen F, Ren W (2019) On the control of multi-agent systems: a survey. In: Foundations and trends in systems and control, vol 6, pp 339\u2013499","DOI":"10.1561\/2600000019"},{"issue":"12","key":"4086_CR6","doi-asserted-by":"publisher","first-page":"12615","DOI":"10.1109\/TIE.2020.3040686","volume":"68","author":"SL Dai","year":"2021","unstructured":"Dai SL, Lu K, Jin X (2021) Fixed-time formation control of unicycle-type mobile robots with visibility and performance constraints. IEEE Trans Ind Electron 68(12):12615\u201312625","journal-title":"IEEE Trans Ind Electron"},{"issue":"9","key":"4086_CR7","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1016\/j.robot.2013.05.004","volume":"61","author":"Z Peng","year":"2013","unstructured":"Peng Z, Wen G, Rahmani A, Yu Y (2013) Leader-follower formation control of nonholonomic mobile robots based on a bioinspired neurodynamic based approach. Robot Auton Syst 61(9):988\u2013996","journal-title":"Robot Auton Syst"},{"issue":"7","key":"4086_CR8","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1017\/S0263574718000218","volume":"36","author":"Y Liu","year":"2018","unstructured":"Liu Y, Bucknall R (2018) A survey of formation control and motion planning of multiple unmanned vehicles. Robotica 36(7):1019\u20131047","journal-title":"Robotica"},{"issue":"6","key":"4086_CR9","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/70.736776","volume":"14","author":"T Balch","year":"1998","unstructured":"Balch T, Arkin RC (1998) Behavior-based formation control for multirobot teams. IEEE Trans Rob Autom 14(6):926\u2013939","journal-title":"IEEE Trans Rob Autom"},{"key":"4086_CR10","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.robot.2016.12.006","volume":"91","author":"H Oh","year":"2017","unstructured":"Oh H, Shirazi AR, Sun C, Jin Y (2017) Bio-inspired self-organising multi-robot pattern formation: a review. Robot Auton Syst 91:83\u2013100","journal-title":"Robot Auton Syst"},{"issue":"4","key":"4086_CR11","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1023\/A:1008814708459","volume":"4","author":"MA Lewis","year":"1997","unstructured":"Lewis MA, Tan KH (1997) High precision formation control of mobile robots using virtual structures. Auton Robot 4(4):387\u2013403","journal-title":"Auton Robot"},{"key":"4086_CR12","doi-asserted-by":"publisher","first-page":"109114","DOI":"10.1016\/j.automatica.2020.109114","volume":"120","author":"E Nu\u00f1o","year":"2020","unstructured":"Nu\u00f1o E, Lor\u00eda A, Hern\u00e1ndez T, Maghenem M, Panteley E (2020) Distributed consensus-formation of force-controlled nonholonomic robots with time-varying delays. Automatica 120:109114","journal-title":"Automatica"},{"issue":"1","key":"4086_CR13","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/TCST.2017.2757448","volume":"27","author":"RR Nair","year":"2019","unstructured":"Nair RR, Behera L, Kumar S (2019) Event-triggered finite-time integral sliding mode controller for consensus-based formation of multirobot systems with disturbances. IEEE Trans Control Syst Technol 27(1):39\u201347","journal-title":"IEEE Trans Control Syst Technol"},{"issue":"12","key":"4086_CR14","first-page":"3162","volume":"67","author":"P Lu","year":"2020","unstructured":"Lu P, Wang H, Zhang F, Yu W, Chen G (2020) Formation control of nonholonomic mobile robots using distributed estimators. IEEE Trans Circuits Syst II Express Briefs 67(12):3162\u20133166","journal-title":"IEEE Trans Circuits Syst II Express Briefs"},{"issue":"5","key":"4086_CR15","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1109\/TNNLS.2018.2861945","volume":"30","author":"J Li","year":"2019","unstructured":"Li J, Chai T, Lewis FL, Ding Z, Jiang Y (2019) Off-policy interleaved q-learning: optimal control for affine nonlinear discrete-time systems. IEEE Trans Neural Netw Learn Syst 30(5):1308\u20131320","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6","key":"4086_CR16","doi-asserted-by":"publisher","first-page":"3405","DOI":"10.1007\/s10489-020-01906-x","volume":"51","author":"W Luo","year":"2021","unstructured":"Luo W, Zhang J, Feng P, Liu H, Yu D, Wu Z (2021) An adaptive adjustment strategy for bolt posture errors based on an improved reinforcement learning algorithm. Appl Intell 51(6):3405\u2013 3420","journal-title":"Appl Intell"},{"issue":"1","key":"4086_CR17","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TCNS.2016.2617622","volume":"5","author":"R Kamalapurkar","year":"2018","unstructured":"Kamalapurkar R, Klotz JR, Walters P, Dixon WE (2018) Model-based reinforcement learning in differential graphical games. IEEE Trans Control Netw Syst 5(1):423\u2013433","journal-title":"IEEE Trans Control Netw Syst"},{"issue":"10","key":"4086_CR18","doi-asserted-by":"publisher","first-page":"4577","DOI":"10.1109\/TNNLS.2020.3023711","volume":"32","author":"W Zhao","year":"2021","unstructured":"Zhao W, Liu H, Lewis FL (2021) Robust formation control for cooperative underactuated quadrotors via reinforcement learning. IEEE Trans Neural Netw Learn Syst 32(10):4577\u20134587","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"9","key":"4086_CR19","doi-asserted-by":"publisher","first-page":"7879","DOI":"10.1109\/TIE.2019.2946545","volume":"67","author":"G Wen","year":"2020","unstructured":"Wen G, Chen CLP, Li B (2020) Optimized formation control using simplified reinforcement learning for a class of multi-agent systems with unknown dynamics. IEEE Trans Ind Electron 67(9):7879\u20137888","journal-title":"IEEE Trans Ind Electron"},{"key":"4086_CR20","doi-asserted-by":"publisher","first-page":"106898","DOI":"10.1016\/j.ast.2021.106898","volume":"117","author":"XN Shi","year":"2021","unstructured":"Shi XN, Zhou D, Chen X, Zhou ZG (2021) Actor-critic-based predefined-time control for spacecraft attitude formation system with guaranteeing prescribed performance on SO(3). Aerosp Sci Technol 117:106898","journal-title":"Aerosp Sci Technol"},{"issue":"10","key":"4086_CR21","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1109\/TNNLS.2016.2585520","volume":"27","author":"B Luo","year":"2016","unstructured":"Luo B, Liu D, Huang TH, Wang D (2016) Model-free optimal tracking control via critic-only q-learning. IEEE Trans Neural Netw Learn Syst 27(10):2134\u20132144","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4086_CR22","doi-asserted-by":"crossref","unstructured":"Balaprakash P, Salim M, Uram TD, Vishwanath V, Wild SM (2018) DeepHyper: asynchronous hyperparameter search for deep neural networks. In: Proceedings -25th IEEE international conference on high performance computing, (HiPC), pp 42\u201351","DOI":"10.1109\/HiPC.2018.00014"},{"issue":"3","key":"4086_CR23","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2020","unstructured":"Chu T, Wang J, Codec\u2018a L, Li Z (2020) Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans Intell Transp Syst 21(3):1086\u20131095","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"5","key":"4086_CR24","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1109\/TNNLS.2012.2236354","volume":"24","author":"X Xu","year":"2013","unstructured":"Xu X, Hou Z, Lian C, He H (2013) Online learning control using adaptive critic designs with sparse kernel machines. IEEE Trans Neural Netw Learn Syst 24(5):762\u2013775","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4086_CR25","doi-asserted-by":"crossref","unstructured":"Wang W, Chen X, Chen L, Wu M (2017) Model-free optimal consensus control for multi-agent systems using kernel-based ADP method. In: 2017 IEEE International conference on systems, man, and cybernetics, (SMC), pp 2471\u20132476","DOI":"10.1109\/SMC.2017.8122994"},{"issue":"11","key":"4086_CR26","doi-asserted-by":"publisher","first-page":"4123","DOI":"10.1109\/TSMC.2018.2883801","volume":"50","author":"W Wang","year":"2020","unstructured":"Wang W, Chen X, Fu H, Wu M (2020) Model-free distributed consensus control based on actor-critic framework for discrete-time nonlinear multiagent systems. IEEE Trans Syst Man Cybern Syst 50 (11):4123\u20134134","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"5","key":"4086_CR27","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1109\/TAC.2017.2750924","volume":"63","author":"S Zhao","year":"2018","unstructured":"Zhao S, Dimarogonas DV, Sun Z, Bauso D (2018) A general approach to coordination control of mobile agents with motion constraints. IEEE Trans Automat Contr 63(5):1509\u20131516","journal-title":"IEEE Trans Automat Contr"},{"issue":"1","key":"4086_CR28","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1109\/TCST.2014.2312324","volume":"23","author":"SM Lee","year":"2015","unstructured":"Lee SM, Kim H, Myung H, Yao X (2015) Cooperative coevolutionary algorithm-based model predictive control guaranteeing stability of multirobot formation. IEEE Trans Control Syst Technol 23(1):37\u201351","journal-title":"IEEE Trans Control Syst Technol"},{"issue":"12","key":"4086_CR29","doi-asserted-by":"publisher","first-page":"3038","DOI":"10.1016\/j.automatica.2014.10.047","volume":"50","author":"MI Abouheaf","year":"2014","unstructured":"Abouheaf MI, Lewis FL, Vamvoudakis KG, Haesaert S, Babuska R (2014) Multi-agent discrete-time graphical games and reinforcement learning solutions. Automatica 50(12):3038\u20133053","journal-title":"Automatica"},{"issue":"5","key":"4086_CR30","doi-asserted-by":"publisher","first-page":"4091","DOI":"10.1109\/TIE.2016.2542134","volume":"64","author":"H Zhang","year":"2017","unstructured":"Zhang H, Jiang H, Luo Y, Xiao G (2017) Data-driven optimal consensus control for discrete-time multi-agent systems with unknown dynamics using reinforcement learning method. IEEE Trans Ind Electron 64(5):4091\u20134100","journal-title":"IEEE Trans Ind Electron"},{"issue":"11","key":"4086_CR31","doi-asserted-by":"publisher","first-page":"6962","DOI":"10.1109\/TSMC.2020.2966631","volume":"51","author":"J Liu","year":"2021","unstructured":"Liu J, Huang Z, Xu X, Zhang X, Sun S, Li D (2021) Multi-kernel online reinforcement learning for path tracking control of intelligent vehicles. IEEE Trans Syst Man Cybern Syst 51(11):6962\u20136975","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"7","key":"4086_CR32","doi-asserted-by":"publisher","first-page":"2362","DOI":"10.1109\/TSMC.2018.2814018","volume":"50","author":"X Zhong","year":"2020","unstructured":"Zhong X, He H (2020) GrHDP solution for optimal consensus control of multiagent discrete-time systems. IEEE Trans Syst Man Cybern Syst 50(7):2362\u20132374","journal-title":"IEEE Trans Syst Man Cybern Syst"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04086-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04086-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04086-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,20]],"date-time":"2023-05-20T10:47:32Z","timestamp":1684579652000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04086-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":32,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["4086"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04086-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]},"assertion":[{"value":"14 August 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}