{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T03:18:14Z","timestamp":1784171894003,"version":"3.55.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T00:00:00Z","timestamp":1719360000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T00:00:00Z","timestamp":1719360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100015956","name":"Special Project for Research and Development in Key areas of Guangdong Province","doi-asserted-by":"publisher","award":["221111210300"],"award-info":[{"award-number":["221111210300"]}],"id":[{"id":"10.13039\/501100015956","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":[[2024,7]]},"DOI":"10.1007\/s11370-024-00544-3","type":"journal-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T17:03:21Z","timestamp":1719421401000},"page":"915-929","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["ETQ-learning: an improved Q-learning algorithm for path planning"],"prefix":"10.1007","volume":"17","author":[{"given":"Huanwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianlv","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongqi","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuyan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5639-9724","authenticated-orcid":false,"given":"Rui","family":"Lou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,26]]},"reference":[{"key":"544_CR1","doi-asserted-by":"crossref","unstructured":"Costa MM, Silva MF (2019) A survey on path planning algorithms for mobile robots. In: 2019 IEEE international conference on autonomous robot systems and competitions (ICARSC), IEEE, pp. 1\u20137","DOI":"10.1109\/ICARSC.2019.8733623"},{"issue":"2","key":"544_CR2","doi-asserted-by":"publisher","first-page":"e0263841","DOI":"10.1371\/journal.pone.0263841","volume":"17","author":"H Wang","year":"2022","unstructured":"Wang H, Lou S, Jing J, Wang Y, Liu W, Liu T (2022) The EBS-A* algorithm: an improved A* algorithm for path planning. PLoS ONE 17(2):e0263841","journal-title":"PLoS ONE"},{"issue":"11","key":"544_CR3","doi-asserted-by":"publisher","first-page":"2213","DOI":"10.3390\/sym13112213","volume":"13","author":"H Wang","year":"2021","unstructured":"Wang H, Qi X, Lou S, Jing J, He H, Liu W (2021) An efficient and robust improved A* algorithm for path planning. Symmetry 13(11):2213","journal-title":"Symmetry"},{"key":"544_CR4","doi-asserted-by":"publisher","first-page":"7664","DOI":"10.1109\/ACCESS.2021.3139534","volume":"10","author":"D Li","year":"2021","unstructured":"Li D, Yin W, Wong WE, Jian M, Chau M (2021) Quality-oriented hybrid path planning based on A* and Q-learning for unmanned aerial vehicle. IEEE Access 10:7664\u20137674","journal-title":"IEEE Access"},{"issue":"4","key":"544_CR5","doi-asserted-by":"publisher","first-page":"6932","DOI":"10.1109\/LRA.2020.3026638","volume":"5","author":"B Wang","year":"2020","unstructured":"Wang B, Liu Z, Li Q, Prorok A (2020) Mobile robot path planning in dynamic environments through globally guided reinforcement learning. IEEE Robot Autom Lett 5(4):6932\u20136939","journal-title":"IEEE Robot Autom Lett"},{"key":"544_CR6","unstructured":"lipei S (2018) Research on intelligent vehicle dynamic path planning algorithm based on improved Q-learning"},{"key":"544_CR7","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"},{"key":"544_CR8","unstructured":"Wang J, Ren Z, Liu T, Yu Y, Zhang C (2020) Qplex: duplex dueling multi-agent Q-learning, arXiv preprint arXiv:2008.01062"},{"key":"544_CR9","unstructured":"Hasselt H (2010) Double Q-learning, Advances in neural information processing systems. 23"},{"issue":"1","key":"544_CR10","first-page":"91","volume":"52","author":"M guojun","year":"2021","unstructured":"guojun M, shimin G (2021) Improved Q-learning algorithm and its application to path planning. J Taiyuan Univ Technol 52(1):91","journal-title":"J Taiyuan Univ Technol"},{"key":"544_CR11","unstructured":"Yunjian P, Jin L (2022) Q-learning path planning based on exploration-exploitation trade-off optimization. Comput Technol Dev. 32(1\u20137)"},{"issue":"5","key":"544_CR12","first-page":"168","volume":"47","author":"W chengbo","year":"2018","unstructured":"chengbo W, zinyu Z, zhiqiang Z, shaobo W (2018) Path planning for unmanned vessels based on Q-learning. Ship Ocean Eng 47(5):168\u2013171","journal-title":"Ship Ocean Eng"},{"key":"544_CR13","unstructured":"Fortunato M, Azar MG, Piot B, Menick J, Osband I, Graves A, Mnih V, Munos R, Hassabis D, Pietquin O et\u00a0al (2017) Noisy networks for exploration, arXiv preprint arXiv:1706.10295"},{"key":"544_CR14","doi-asserted-by":"crossref","unstructured":"Ates U (2020) Long-term planning with deep reinforcement learning on autonomous drones. In: Innovations in intelligent systems and applications conference (ASYU). IEEE 2020:1\u20136","DOI":"10.1109\/ASYU50717.2020.9259811"},{"issue":"12","key":"544_CR15","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.cja.2020.12.027","volume":"34","author":"H Zijian","year":"2021","unstructured":"Zijian H, Xiaoguang G, Kaifang W, Yiwei Z, Qianglong W (2021) Relevant experience learning: a deep reinforcement learning method for UAV autonomous motion planning in complex unknown environments. Chin J Aeronaut 34(12):187\u2013204","journal-title":"Chin J Aeronaut"},{"key":"544_CR16","unstructured":"Schulman J, Levine S, Abbeel P, Jordan M, Moritz P (2015) Trust region policy optimization. In: International conference on machine learning, PMLR, pp. 1889\u20131897"},{"key":"544_CR17","doi-asserted-by":"crossref","unstructured":"Zhang T, Huo X, Chen S, Yang B, Zhang G (2018) Hybrid path planning of a quadrotor UAV based on q-learning algorithm. In: 37th Chinese control conference (CCC). IEEE 5415\u20135419","DOI":"10.23919\/ChiCC.2018.8482604"},{"key":"544_CR18","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms, arXiv preprint arXiv:1707.06347"},{"key":"544_CR19","unstructured":"Andrychowicz M, Wolski F, Ray A, Schneider J, Fong R, Welinder P, McGrew B, Tobin J, Pieter\u00a0Abbeel O, Zaremba W (2017) Hindsight experience replay, Advances in neural information processing systems 30"},{"key":"544_CR20","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, PMLR, pp. 1861\u20131870"},{"key":"544_CR21","first-page":"18560","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar A, Gupta A, Levine S (2020) Discor: corrective feedback in reinforcement learning via distribution correction. Adv Neural Inf Process Syst 33:18560\u201318572","journal-title":"Adv Neural Inf Process Syst"},{"key":"544_CR22","first-page":"11063","volume":"35","author":"D Kong","year":"2022","unstructured":"Kong D, Yang L (2022) Provably feedback-efficient reinforcement learning via active reward learning. Adv Neural Inf Process Syst 35:11063\u201311078","journal-title":"Adv Neural Inf Process Syst"},{"key":"544_CR23","doi-asserted-by":"crossref","unstructured":"Song Y, Steinweg M, Kaufmann E, Scaramuzza D (2021) Autonomous drone racing with deep reinforcement learning. In: 2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp. 1205\u20131212","DOI":"10.1109\/IROS51168.2021.9636053"},{"issue":"4","key":"544_CR24","first-page":"203","volume":"18","author":"Z Wang","year":"2021","unstructured":"Wang Z, Yang H, Wu Q, Zheng J (2021) Fast path planning for unmanned aerial vehicles by self-correction based on Q-learning. J Aerosp Inf Syst 18(4):203\u2013211","journal-title":"J Aerosp Inf Syst"},{"key":"544_CR25","doi-asserted-by":"crossref","unstructured":"Yan C, Xiang X (2018) A path planning algorithm for UAV based on improved q-learning. In: 2nd international conference on robotics and automation sciences (ICRAS). IEEE :1\u20135","DOI":"10.1109\/ICRAS.2018.8443226"},{"key":"544_CR26","doi-asserted-by":"crossref","unstructured":"de\u00a0Carvalho KB, de\u00a0Oliveira IRL, Villa DK, Caldeira AG, Sarcinelli-Filho M, Brand\u00e3o AS (2022) Q-learning based path planning method for UAVs using priority shifting. In: 2022 International Conference on Unmanned Aircraft Systems (ICUAS), IEEE, pp. 421\u2013426","DOI":"10.1109\/ICUAS54217.2022.9836175"},{"key":"544_CR27","doi-asserted-by":"crossref","unstructured":"Li S, Xu X, Zuo L (2015) Dynamic path planning of a mobile robot with improved Q-learning algorithm. In: IEEE international conference on information and automation. IEEE 409\u2013414","DOI":"10.1109\/ICInfA.2015.7279322"},{"key":"544_CR28","doi-asserted-by":"crossref","unstructured":"Wang Y, Wang S, Xie Y, Hu Y, Li H (2022) Q-learning-based collision-free path planning for mobile robot in unknown environment. In: 2022 IEEE 17th conference on industrial electronics and applications (ICIEA), IEEE, pp. 1104\u20131109","DOI":"10.1109\/ICIEA54703.2022.10006304"}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-024-00544-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11370-024-00544-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-024-00544-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T13:26:22Z","timestamp":1721654782000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11370-024-00544-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,26]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["544"],"URL":"https:\/\/doi.org\/10.1007\/s11370-024-00544-3","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"value":"1861-2776","type":"print"},{"value":"1861-2784","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,26]]},"assertion":[{"value":"27 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 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 they do not have any 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":"All authors agreed to participate the research.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"All authors read and approved the final manuscript.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}]}}