{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:33:42Z","timestamp":1784014422784,"version":"3.55.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant 52275003"],"award-info":[{"award-number":["Grant 52275003"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009110","name":"Natural Science Foundation of Xinjiang Uygur Autonomous Region","doi-asserted-by":"crossref","award":["Grant 2022D01C673"],"award-info":[{"award-number":["Grant 2022D01C673"]}],"id":[{"id":"10.13039\/100009110","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["buctrc202105"],"award-info":[{"award-number":["buctrc202105"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Intel Serv Robotics"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s11370-024-00514-9","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T16:02:28Z","timestamp":1709222548000},"page":"621-630","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Memory-based soft actor\u2013critic with prioritized experience replay for autonomous navigation"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4043-8478","authenticated-orcid":false,"given":"Zhigang","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wendong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teng","family":"Ran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianping","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,29]]},"reference":[{"issue":"17","key":"514_CR1","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.1049\/iet-cta.2018.6125","volume":"13","author":"X Bai","year":"2019","unstructured":"Bai X, Yan W, Cao M, Xue D (2019) Distributed multi-vehicle task assignment in a time-invariant drift field with obstacles. IET Control Theory Appl 13(17):2886\u20132893","journal-title":"IET Control Theory Appl"},{"key":"514_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11370-023-00470-w","volume":"16","author":"H Eqab","year":"2023","unstructured":"Eqab H, Salamah YB, Ahmad I, Morsy M (2023) Development of source seeking algorithm for mobile robots. Intell Serv Robot 16:1\u20139","journal-title":"Intell Serv Robot"},{"key":"514_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102440","volume":"78","author":"W Xiao","year":"2023","unstructured":"Xiao W, Yuan L, Ran T, He L, Zhang J, Cui J (2023) Multimodal fusion for autonomous navigation via deep reinforcement learning with sparse rewards and hindsight experience replay. Displays 78:102440","journal-title":"Displays"},{"key":"514_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11370-023-00461-x","volume":"16","author":"GJ Paz-Delgado","year":"2023","unstructured":"Paz-Delgado GJ, P\u00e9rez-del-Pulgar CJ, Azkarate M, Kirchner F, Garc\u00eda-Cerezo A (2023) Multi-stage warm started optimal motion planning for over-actuated mobile platforms. Intell Serv Robot 16:1\u201317","journal-title":"Intell Serv Robot"},{"key":"514_CR5","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s11370-021-00352-z","volume":"14","author":"Q Chen","year":"2021","unstructured":"Chen Q, Lu Y, Wang Y, Zhu B (2021) From topological map to local cognitive map: a new opportunity of local path planning. Intell Serv Robot 14:285\u2013301","journal-title":"Intell Serv Robot"},{"issue":"4","key":"514_CR6","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1109\/TII.2019.2936167","volume":"16","author":"H Shi","year":"2019","unstructured":"Shi H, Shi L, Xu M, Hwang K-S (2019) End-to-end navigation strategy with deep reinforcement learning for mobile robots. IEEE Trans Ind Inform 16(4):2393\u20132402","journal-title":"IEEE Trans Ind Inform"},{"key":"514_CR7","first-page":"1","volume":"71","author":"W Xiao","year":"2022","unstructured":"Xiao W, Yuan L, He L, Ran T, Zhang J, Cui J (2022) Multigoal visual navigation with collision avoidance via deep reinforcement learning. IEEE Trans Instrum Meas 71:1\u20139","journal-title":"IEEE Trans Instrum Meas"},{"key":"514_CR8","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/s11370-021-00387-2","volume":"14","author":"J Choi","year":"2021","unstructured":"Choi J, Lee G, Lee C (2021) Reinforcement learning-based dynamic obstacle avoidance and integration of path planning. Intell Serv Robot 14:663\u2013677","journal-title":"Intell Serv Robot"},{"key":"514_CR9","doi-asserted-by":"publisher","first-page":"29064","DOI":"10.1109\/ACCESS.2020.2971780","volume":"8","author":"B Li","year":"2020","unstructured":"Li B, Wu Y (2020) Path planning for UAV ground target tracking via deep reinforcement learning. IEEE Access 8:29064\u201329074","journal-title":"IEEE Access"},{"key":"514_CR10","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.robot.2019.02.013","volume":"115","author":"ES Low","year":"2019","unstructured":"Low ES, Ong P, Cheah KC (2019) Solving the optimal path planning of a mobile robot using improved q-learning. Robot Auton Syst 115:143\u2013161","journal-title":"Robot Auton Syst"},{"key":"514_CR11","doi-asserted-by":"crossref","unstructured":"Bai Z, Cai B, ShangGuan W, Chai L (2018) Deep learning based motion planning for autonomous vehicle using spatiotemporal LSTM network. IEEE, pp 1610\u20131614","DOI":"10.1109\/CAC.2018.8623233"},{"key":"514_CR12","doi-asserted-by":"crossref","unstructured":"Everett M, Chen YF, How JP (2018) Motion planning among dynamic, decision-making agents with deep reinforcement learning. IEEE, pp 3052\u20133059","DOI":"10.1109\/IROS.2018.8593871"},{"issue":"8","key":"514_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"514_CR14","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv preprint https:\/\/arxiv.org\/abs\/1511.05952"},{"key":"514_CR15","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap T, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. PMLR, pp 1928\u20131937"},{"key":"514_CR16","doi-asserted-by":"crossref","unstructured":"Chen C, Liu Y, Kreiss S, Alahi A (2019) Crowd-robot interaction: crowd-aware robot navigation with attention-based deep reinforcement learning. IEEE, pp 6015\u20136022","DOI":"10.1109\/ICRA.2019.8794134"},{"issue":"7540","key":"514_CR17","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"514_CR18","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing ATARI with deep reinforcement learning. https:\/\/arxiv.org\/abs\/1312.5602"},{"issue":"1","key":"514_CR19","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1007\/s11227-021-03878-2","volume":"78","author":"J Li","year":"2022","unstructured":"Li J, Chen Y, Zhao X, Huang J (2022) An improved DQN path planning algorithm. J Supercomput 78(1):616\u2013639","journal-title":"J Supercomput"},{"key":"514_CR20","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. https:\/\/arxiv.org\/abs\/1509.02971"},{"key":"514_CR21","doi-asserted-by":"crossref","unstructured":"Tai L, Paolo G, Liu M (2017) Virtual-to-real deep reinforcement learning: continuous control of mobile robots for Mapless navigation. IEEE, pp 31\u201336","DOI":"10.1109\/IROS.2017.8202134"},{"key":"514_CR22","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. PMLR, pp 1861\u20131870"},{"key":"514_CR23","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/BF00992699","volume":"8","author":"L-J Lin","year":"1992","unstructured":"Lin L-J (1992) Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach Learn 8:293\u2013321","journal-title":"Mach Learn"},{"issue":"2","key":"514_CR24","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10846-021-01367-5","volume":"102","author":"JC Jesus","year":"2021","unstructured":"Jesus JC, Kich VA, Kolling AH, Grando RB, Cuadros MASL, Gamarra DFT (2021) Soft actor-critic for navigation of mobile robots. J Intell Robot Syst 102(2):31","journal-title":"J Intell Robot Syst"},{"key":"514_CR25","unstructured":"Li AA, Lu Z, Miao C (2021) Revisiting prioritized experience replay: a value perspective. https:\/\/arxiv.org\/abs\/2102.03261"},{"key":"514_CR26","doi-asserted-by":"crossref","unstructured":"Zha D, Lai K-H, Zhou K, Hu X (2019) Experience replay optimization. https:\/\/arxiv.org\/abs\/1906.08387","DOI":"10.24963\/ijcai.2019\/589"},{"key":"514_CR27","doi-asserted-by":"crossref","unstructured":"Inoue M, Yamashita T, Nishida T (2019) Robot path planning by LSTM network under changing environment. Springer, pp 317\u2013329","DOI":"10.1007\/978-981-13-0341-8_29"},{"key":"514_CR28","doi-asserted-by":"publisher","first-page":"11253","DOI":"10.1109\/JSEN.2023.3237206","volume":"23","author":"J Cui","year":"2023","unstructured":"Cui J, Yuan L, He L, Xiao W, Ran T, Zhang J (2023) Multi-input autonomous driving based on deep reinforcement learning with double bias experience replay. IEEE Sens J 23:11253\u201311261","journal-title":"IEEE Sens J"},{"issue":"5","key":"514_CR29","doi-asserted-by":"publisher","first-page":"5342","DOI":"10.1109\/TIE.2021.3078353","volume":"69","author":"K Wu","year":"2021","unstructured":"Wu K, Wang H, Esfahani MA, Yuan S (2021) Learn to navigate autonomously through deep reinforcement learning. IEEE Trans Ind Electron 69(5):5342\u20135352","journal-title":"IEEE Trans Ind Electron"},{"issue":"1","key":"514_CR30","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10845-022-01988-z","volume":"34","author":"C Zhou","year":"2023","unstructured":"Zhou C, Huang B, Hassan H, Fr\u00e4nti P (2023) Attention-based advantage actor-critic algorithm with prioritized experience replay for complex 2-d robotic motion planning. J Intell Manuf 34(1):151\u2013180","journal-title":"J Intell Manuf"}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-024-00514-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11370-024-00514-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-024-00514-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T17:09:05Z","timestamp":1716656945000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11370-024-00514-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,29]]},"references-count":30,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["514"],"URL":"https:\/\/doi.org\/10.1007\/s11370-024-00514-9","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"value":"1861-2776","type":"print"},{"value":"1861-2784","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,29]]},"assertion":[{"value":"25 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 February 2024","order":3,"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 the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}