{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:01:55Z","timestamp":1781622115501,"version":"3.54.5"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702023"],"award-info":[{"award-number":["61702023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976014"],"award-info":[{"award-number":["61976014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3057485","type":"journal-article","created":{"date-parts":[[2021,2,8]],"date-time":"2021-02-08T23:32:19Z","timestamp":1612827139000},"page":"24884-24900","source":"Crossref","is-referenced-by-count":144,"title":["Unmanned Aerial Vehicle Path Planning Algorithm Based on Deep Reinforcement Learning in Large-Scale and Dynamic Environments"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5762-5093","authenticated-orcid":false,"given":"Ronglei","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2769-4343","authenticated-orcid":false,"given":"Zhijun","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5051-5991","authenticated-orcid":false,"given":"Lifeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9388-2297","authenticated-orcid":false,"given":"Haochen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8123-9846","authenticated-orcid":false,"given":"Kaipeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2095-0180","authenticated-orcid":false,"given":"Zhe","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref38","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9918-3"},{"key":"ref32","first-page":"237","article-title":"Realtime simultaneous localization and mapping for UAV: A survey","author":"li","year":"2016","journal-title":"Proc Int Micro Air Vehicle Conf Competition (IMAV)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0292-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-012-0119-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2432455"},{"key":"ref10","first-page":"3790","article-title":"UAV path planning method based on ant colony optimization","author":"zhang","year":"2010","journal-title":"Proc Chin Control Decis Conf"},{"key":"ref40","first-page":"323","article-title":"Self-improvement based on reinforcement learning","volume":"6","author":"lin","year":"1991","journal-title":"Planning Teaching Mach Learn Proc"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1712","DOI":"10.1016\/j.asoc.2007.10.011","article-title":"A modified ant optimization algorithm for path planning of UCAV","volume":"8","author":"chen","year":"2008","journal-title":"Appl Soft Comput"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-007-9149-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2019.03.026"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA.2007.4318681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2009.10.006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2514\/6.2007-2815"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2812896"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.10.012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.04.021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/net.20438"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9901-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2001.931933"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_71"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3477.552194"},{"key":"ref8","first-page":"215","article-title":"Application of genetic algorithm in path planning","volume":"34","author":"meng","year":"2008","journal-title":"Eng Comput"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/116873.116880"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9293-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2015.12.008"},{"key":"ref1","first-page":"2899","article-title":"Reinforcement learning with autonomous small unmanned aerial vehicles cluttered environments","author":"tran","year":"2015","journal-title":"Proc AIAA Aviation Technol Integr Oper Conf"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref22","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref24","article-title":"Deep recurrent Q-Learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"arXiv 1507 06527"},{"key":"ref23","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref26","first-page":"2722","article-title":"Deep driving: Learning affordance for direct perception in autonomous driving","author":"chen","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09348925.pdf?arnumber=9348925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:41Z","timestamp":1639771001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9348925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3057485","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}