{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T12:01:06Z","timestamp":1775304066843,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T00:00:00Z","timestamp":1544486400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61703372"],"award-info":[{"award-number":["61703372"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Key Scientific Research Project of Henan Higher Education","award":["18A413012"],"award-info":[{"award-number":["18A413012"]}]},{"DOI":"10.13039\/501100010031","name":"Postdoctoral Research Foundation of China","doi-asserted-by":"publisher","award":["2016M592311"],"award-info":[{"award-number":["2016M592311"]}],"id":[{"id":"10.13039\/501100010031","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Science&Technology Innovation Team Project of Henan Province","award":["17IRTSTHN013"],"award-info":[{"award-number":["17IRTSTHN013"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Prog Artif Intell"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s13748-018-00168-6","type":"journal-article","created":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T03:29:06Z","timestamp":1544498946000},"page":"133-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Path planning of a mobile robot in a free-space environment using Q-learning"],"prefix":"10.1007","volume":"8","author":[{"given":"Jianxun","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1024-4135","authenticated-orcid":false,"given":"Jianbin","family":"Xin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,11]]},"reference":[{"issue":"9","key":"168_CR1","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.5897\/IJPS11.1745","volume":"7","author":"P Raja","year":"2012","unstructured":"Raja, P., Pugazhenthi, S.: Optimal path planning of mobile robots: a review. Int. J. Phys. Sci. 7(9), 1314\u20131320 (2012)","journal-title":"Int. J. Phys. Sci."},{"issue":"1","key":"168_CR2","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1109\/TIE.2013.2245612","volume":"61","author":"H Rezaee","year":"2013","unstructured":"Rezaee, H., Abdollahi, F.: A decentralized cooperative control scheme with obstacle avoidance for a team of mobile robots. IEEE Trans. Ind. Electron. 61(1), 347\u2013354 (2013)","journal-title":"IEEE Trans. Ind. Electron."},{"key":"168_CR3","doi-asserted-by":"crossref","unstructured":"Parasuraman, S., Ganapathy, V., Shirinzadeh, B.: Multiple sensors data integration using MFAM for mobile robot navigation. In: IEEE Congress on Evolutionary Computation, pp. 2421\u20132427 (2007)","DOI":"10.1109\/CEC.2007.4424774"},{"issue":"3","key":"168_CR4","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1109\/TSMCB.2008.2008561","volume":"39","author":"C Cai","year":"2009","unstructured":"Cai, C., Ferrari, S.: Information-driven sensor path planning by approximate cell decomposition. IEEE Trans. Syst. Man Cybern. Part B Cybern. 39(3), 672\u2013689 (2009)","journal-title":"IEEE Trans. Syst. Man Cybern. Part B Cybern."},{"issue":"3","key":"168_CR5","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/s10514-012-9304-1","volume":"33","author":"S Bhattacharya","year":"2012","unstructured":"Bhattacharya, S., Likhachev, M., Kumar, V.: Topological constraints in search-based robot path planning. Auton. Robots 33(3), 273\u2013290 (2012)","journal-title":"Auton. Robots"},{"issue":"1\u20132","key":"168_CR6","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/s10846-009-9318-x","volume":"56","author":"G Zhang","year":"2009","unstructured":"Zhang, G., Ferrari, S., Qian, M.: An information roadmap method for robotic sensor path planning. J. Intell. Robot. Syst. 56(1\u20132), 69\u201398 (2009)","journal-title":"J. Intell. Robot. Syst."},{"key":"168_CR7","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.asoc.2015.01.067","volume":"30","author":"MA Contreras-Cruz","year":"2015","unstructured":"Contreras-Cruz, M.A., Ayala-Ramirez, V., Hernandez-Belmonte, U.H.: Mobile robot path planning using artificial bee colony and evolutionary programming. Appl. Soft Comput. 30, 319\u2013328 (2015)","journal-title":"Appl. Soft Comput."},{"issue":"10","key":"168_CR8","doi-asserted-by":"publisher","first-page":"4813","DOI":"10.1109\/TIE.2011.2109332","volume":"58","author":"CC Tsai","year":"2011","unstructured":"Tsai, C.C., Huang, H.C., Chan, C.K.: Parallel elite genetic algorithm and its application to global path planning for autonomous robot navigation. IEEE Trans. Ind. Electron. 58(10), 4813\u20134821 (2011)","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"5","key":"168_CR9","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1016\/j.amc.2013.07.022","volume":"222","author":"H Miao","year":"2013","unstructured":"Miao, H., Tian, Y.C.: Dynamic robot path planning using an enhanced simulated annealing approach. Appl. Math. Comput. 222(5), 420\u2013437 (2013)","journal-title":"Appl. Math. Comput."},{"issue":"1","key":"168_CR10","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/S0004-3702(03)00114-0","volume":"152","author":"E Remolina","year":"2004","unstructured":"Remolina, E., Kuipers, B.: Towards a general theory of topological maps. Artif. Intell. 152(1), 47\u2013104 (2004)","journal-title":"Artif. Intell."},{"issue":"6","key":"168_CR11","doi-asserted-by":"crossref","first-page":"2913","DOI":"10.3233\/IFS-130957","volume":"26","author":"B Sun","year":"2014","unstructured":"Sun, B., et al.: A novel fuzzy control algorithm for three-dimensional AUV path planning based on sonar model. J. Intell. Fuzzy Syst. 26(6), 2913\u20132926 (2014)","journal-title":"J. Intell. Fuzzy Syst."},{"issue":"11","key":"168_CR12","doi-asserted-by":"publisher","first-page":"1724","DOI":"10.1109\/TNN.2009.2029858","volume":"20","author":"H Qu","year":"2009","unstructured":"Qu, H., et al.: Real-time robot path planning based on a modified pulse-coupled neural network model. IEEE Trans. Neural Netw. 20(11), 1724\u201339 (2009)","journal-title":"IEEE Trans. Neural Netw."},{"key":"168_CR13","first-page":"3357","volume":"2017","author":"Y Zhu","year":"2017","unstructured":"Zhu, Y., et al.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. IEEE Int. Conf. Robot. Autom. 2017, 3357\u20133364 (2017)","journal-title":"IEEE Int. Conf. Robot. Autom."},{"issue":"3\u20134","key":"168_CR14","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"168_CR15","doi-asserted-by":"crossref","unstructured":"Gomes, E.R., Kowalczyk, R.: Modelling the dynamics of multiagent Q-learning with $$\\epsilon $$ \u03f5 -greedy exploration. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 1181\u20131182 (2009)","DOI":"10.65109\/DYIY4538"},{"key":"168_CR16","unstructured":"Kim, I., et al.: Obstacle avoidance path planning for UAV using reinforcement learning under simulated environment. In: IASER 3rd International Conference on Electronics, Electrical Engineering, Computer Science, Okinawa, pp. 34\u201336 (2017)"},{"issue":"5","key":"168_CR17","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1109\/TSMCA.2012.2227719","volume":"43","author":"A Konar","year":"2013","unstructured":"Konar, A., Indrani, G., Sapam, J.S., Lakhmi, C.J., Atulya, K.N.: A deterministic improved Q-learning for path planning of a mobile robot. IEEE Trans. Syst. Man Cybern. Syst. 43(5), 1141\u20131153 (2013)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"168_CR18","first-page":"15211","volume":"7","author":"R Nirmalya","year":"2017","unstructured":"Nirmalya, R., et al.: Implementation of image processing and reinforcement learning in path planning of mobile robots. Int. J. Eng. Sci. 7, 15211 (2017)","journal-title":"Int. J. Eng. Sci."},{"issue":"5","key":"168_CR19","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/TCYB.2016.2542923","volume":"47","author":"Q Wei","year":"2017","unstructured":"Wei, Q., Frank, L.L., Sun, Q., Yan, P., Song, R.: Discrete-time deterministic Q-learning: a novel convergence analysis. IEEE Trans. Cybern. 47(5), 1224\u20131237 (2017)","journal-title":"IEEE Trans. Cybern."},{"key":"168_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., Wei, Q., Xu, L.: Multi-step reinforcement learning algorithm of mobile robot path planning based on virtual potential field. In: International Conference of Pioneering Computer Scientists, Engineers and Educators, Singapore, pp. 528\u2013538 (2017)","DOI":"10.1007\/978-981-10-6388-6_45"},{"key":"168_CR21","doi-asserted-by":"crossref","unstructured":"Li, S., Xin, X., Lei, Z.: Dynamic path planning of a mobile robot with improved Q-learning algorithm. In: IEEE International Conference on Information and Automation, pp. 409\u2013411 (2015)","DOI":"10.1109\/ICInfA.2015.7279322"},{"key":"168_CR22","unstructured":"Lee, K., et al.: Deep reinforcement learning in continuous action spaces: a case study in the game of simulated curling. In: International Conference on Machine Learning, pp. 2943\u20132952 (2018)"},{"key":"168_CR23","unstructured":"Luuk, A., Heskes, T., de Vries, A. P.: Comparing discretization methods for applying Q-learning in continuous state-action space (2017)"},{"issue":"1","key":"168_CR24","first-page":"48","volume":"29","author":"E Keogh","year":"2017","unstructured":"Keogh, E., Mueen, A.: Curse of dimensionality. Ind. Eng. Chem 29(1), 48\u201353 (2017)","journal-title":"Ind. Eng. Chem"},{"key":"168_CR25","doi-asserted-by":"crossref","unstructured":"Cai, J., Yu, R., Cheng, L.: Autonomous navigation research for mobile robot. In: The World Congress on Intelligent Control and Automation, pp. 331\u2013335 (2012)","DOI":"10.1109\/WCICA.2012.6357893"},{"key":"168_CR26","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71795-9","volume-title":"The Fuzzification of Systems: The Genesis of Fuzzy Set Theory and Its Initial Applications","author":"R Seising","year":"2007","unstructured":"Seising, R.: The Fuzzification of Systems: The Genesis of Fuzzy Set Theory and Its Initial Applications. Springer, Berlin (2007)"},{"issue":"3","key":"168_CR27","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.sysconle.2007.08.014","volume":"57","author":"AK Sanyal","year":"2008","unstructured":"Sanyal, A.K., et al.: Global optimal attitude estimation using uncertainty ellipsoids. Syst. Control Lett. 57(3), 236\u2013245 (2008)","journal-title":"Syst. Control Lett."},{"key":"168_CR28","unstructured":"Dearden, R., Friedman, N., Russell, S.: Bayesian Q-learning. In: AAAI\/IAAI, pp. 761\u2013768 (1998)"},{"issue":"4","key":"168_CR29","doi-asserted-by":"publisher","first-page":"041145","DOI":"10.1103\/PhysRevE.85.041145","volume":"85","author":"A Kianercy","year":"2012","unstructured":"Kianercy, A., Galstyan, A.: Dynamics of Boltzmann Q-learning in two-player two-action games. Phys. Rev. E 85(4), 041145 (2012)","journal-title":"Phys. Rev. E"},{"key":"168_CR30","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"}],"container-title":["Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13748-018-00168-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13748-018-00168-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13748-018-00168-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T11:11:34Z","timestamp":1775301094000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13748-018-00168-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["168"],"URL":"https:\/\/doi.org\/10.1007\/s13748-018-00168-6","relation":{},"ISSN":["2192-6352","2192-6360"],"issn-type":[{"value":"2192-6352","type":"print"},{"value":"2192-6360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,11]]},"assertion":[{"value":"22 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}