{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T04:33:51Z","timestamp":1782362031982,"version":"3.54.5"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T00:00:00Z","timestamp":1658361600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T00:00:00Z","timestamp":1658361600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U1933123"],"award-info":[{"award-number":["U1933123"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s00500-022-07293-4","type":"journal-article","created":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T21:02:37Z","timestamp":1658437357000},"page":"8961-8970","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Research on path planning algorithm of mobile robot based on reinforcement learning"],"prefix":"10.1007","volume":"26","author":[{"given":"Guoqian","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongquan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7084-0297","authenticated-orcid":false,"given":"Xinzhi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,21]]},"reference":[{"issue":"3","key":"7293_CR1","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s00500-006-0068-4","volume":"11","author":"O Castillo","year":"2007","unstructured":"Castillo O, Trujillo L, Melin P (2007) Multiple objective genetic algorithms for path-planning optimization in autonomous mobile robots. Soft Comput 11(3):269\u2013279","journal-title":"Soft Comput"},{"key":"7293_CR2","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-662-47487-7_24","volume":"352","author":"P Chu","year":"2015","unstructured":"Chu P, Vu H, Yeo D, Lee B, Cho K (2015) Robot reinforcement learning for automatically avoiding a dynamic obstacle in a virtual environment. Lecture Notes Electr Eng 352:157\u2013164","journal-title":"Lecture Notes Electr Eng"},{"issue":"5","key":"7293_CR3","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1109\/TSMCB.2004.832154","volume":"34","author":"M Guo","year":"2004","unstructured":"Guo M, Liu Y, Malec J (2004) A new q-learning algorithm based on the metropolis criterion. IEEE Trans Syst Man Cybern Part B Cybern 34(5):2140\u20132143","journal-title":"IEEE Trans Syst Man Cybern Part B Cybern"},{"issue":"1","key":"7293_CR4","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.rcim.2010.06.019","volume":"27","author":"MAK Jaradat","year":"2011","unstructured":"Jaradat MAK, Al-Rousan M, Quadan L (2011) Reinforcement based mobile robot navigation in dynamic environment. Robot Comput-Integr Manuf 27(1):135\u2013149","journal-title":"Robot Comput-Integr Manuf"},{"key":"7293_CR5","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.3390\/sym13061057","volume":"13","author":"Z Lieping","year":"2021","unstructured":"Lieping Z, Liu T, Shenglan Z, Zhengzhong W, Xianhao S, Zuqiong Z (2021) A self-adaptive reinforcement-exploration q-learning algorithm. Symmetry 13:1057","journal-title":"Symmetry"},{"issue":"1","key":"7293_CR6","doi-asserted-by":"publisher","first-page":"S177","DOI":"10.1016\/S1672-6529(09)60233-X","volume":"7","author":"L Lin","year":"2010","unstructured":"Lin L, Xie H, Zhang D, Shen L (2010) Supervised neural q-learning based motion control for bionic underwater robots. J Bionic Eng 7(1):S177\u2013S184","journal-title":"J Bionic Eng"},{"key":"7293_CR7","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/TVT.2018.2882130","volume":"68","author":"YN Ma","year":"2018","unstructured":"Ma YN, Gong YJ, Xiao CF, Gao Y, Zhang J (2018) Path planning for autonomous underwater vehicles: an ant colony algorithm incorporating alarm pheromone. IEEE Trans Veh Technol 68:141\u2013154","journal-title":"IEEE Trans Veh Technol"},{"key":"7293_CR8","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.robot.2016.08.001","volume":"86","author":"TT Mac","year":"2016","unstructured":"Mac TT, Copot C, Tran DT, Keyser RD (2016) Heuristic approaches in robot path planning: a survey. Robot Auton Syst 86:13\u201328","journal-title":"Robot Auton Syst"},{"issue":"2","key":"7293_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-017-0468-y","volume":"86","author":"AS Polydoros","year":"2017","unstructured":"Polydoros AS, Nalpantidis L (2017) Survey of model-based reinforcement learning: applications on robotics. J Intell Robot Syst 86(2):1\u201321","journal-title":"J Intell Robot Syst"},{"key":"7293_CR10","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/70.163777","volume":"8","author":"E Rimon","year":"1992","unstructured":"Rimon E, Koditschek DE (1992) Exact robot navigation using artificial potential functions. IEEE Trans Robot Autom 8:501\u2013518","journal-title":"IEEE Trans Robot Autom"},{"issue":"012","key":"7293_CR11","first-page":"1623","volume":"29","author":"Y Song","year":"2012","unstructured":"Song Y, Li Y, Li C (2012) Initialization of reinforcement learning for mobile robot path planning. Control Theory Appl 29(012):1623\u20131628","journal-title":"Control Theory Appl"},{"issue":"99","key":"7293_CR12","first-page":"143","volume":"115","author":"LE Soong","year":"2019","unstructured":"Soong LE, Pauline O, Chun CK (2019) Solving the optimal path planning of a mobile robot using improved q-learning. Robot Auton Syst 115(99):143\u2013161","journal-title":"Robot Auton Syst"},{"issue":"3\u20134","key":"7293_CR13","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8(3\u20134):279\u2013292","journal-title":"Mach Learn"},{"issue":"3","key":"7293_CR14","first-page":"314","volume":"27","author":"X Xu","year":"2019","unstructured":"Xu X, Yuan J (2019) Path planning method for mobile robot based on improved reinforcement learning. J Chin Inert Technol 27(3):314\u2013320","journal-title":"J Chin Inert Technol"},{"key":"7293_CR15","doi-asserted-by":"publisher","first-page":"63","DOI":"10.3389\/fnbot.2020.00063","volume":"14","author":"J Yu","year":"2020","unstructured":"Yu J, Su Y, Liao Y (2020) The path planning of mobile robot by neural networks and hierarchical reinforcement learning. Front Neurorobot 14:63","journal-title":"Front Neurorobot"},{"issue":"12","key":"7293_CR16","first-page":"65","volume":"46","author":"F Zhang","year":"2018","unstructured":"Zhang F, Li N, Yuan R, Fu Y (2018) Robot path planning algorithm based on reinforcement learning. J Huazhong Univ Sci Technol (Nat Sci Ed) 46(12):65\u201370","journal-title":"J Huazhong Univ Sci Technol (Nat Sci Ed)"},{"issue":"1","key":"7293_CR17","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.neucom.2012.09.019","volume":"103","author":"Y Zhang","year":"2013","unstructured":"Zhang Y, Gong DW, Zhang JH (2013) Robot path planning in uncertain environment using multi-objective particle swarm optimization. Neurocomputing 103(1):172\u2013185","journal-title":"Neurocomputing"},{"key":"7293_CR18","doi-asserted-by":"publisher","first-page":"47824","DOI":"10.1109\/ACCESS.2020.2978077","volume":"8","author":"M Zhao","year":"2020","unstructured":"Zhao M, Lu H, Yang S, Guo F (2020) The experience-memory q-learning algorithm for robot path planning in unknown environment. IEEE Access 8:47824\u201347844","journal-title":"IEEE Access"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-022-07293-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-022-07293-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-022-07293-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T16:24:19Z","timestamp":1660753459000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-022-07293-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,21]]},"references-count":18,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["7293"],"URL":"https:\/\/doi.org\/10.1007\/s00500-022-07293-4","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,21]]},"assertion":[{"value":"10 May 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Informed consent was obtained from all individual participants included in the study","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}