{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:22:16Z","timestamp":1792599736933,"version":"4.5.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2016YFB0100902"],"award-info":[{"award-number":["2016YFB0100902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1109\/tvt.2018.2890773","type":"journal-article","created":{"date-parts":[[2019,1,3]],"date-time":"2019-01-03T14:47:51Z","timestamp":1546526871000},"page":"2124-2136","source":"Crossref","is-referenced-by-count":431,"title":["Autonomous Navigation of UAVs in Large-Scale Complex Environments: A Deep Reinforcement Learning Approach"],"prefix":"10.1109","volume":"68","author":[{"given":"Chao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7683-6937","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9396-1964","authenticated-orcid":false,"given":"Yuan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref32","first-page":"466","article-title":"Policy gradient critics","author":"wierstra","year":"0","journal-title":"Proc Eur Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1966407.1966411","article-title":"Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs","volume":"7","author":"jur?\u00ed?ek","year":"2011","journal-title":"ACM Trans Speech Lang Process"},{"key":"ref30","first-page":"697","article-title":"Solving deep memory POMDPs with recurrent policy gradients","author":"wierstra","year":"0","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref37","article-title":"Memory-based control with recurrent neural networks","author":"heess","year":"2015"},{"key":"ref36","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref35","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref34","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0292-1"},{"key":"ref40","first-page":"2652","article-title":"Expressing arbitrary reward functions as potential-based advice","author":"harutyunyan","year":"0","journal-title":"Proc Assoc Advance Artif Intell"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2016.7804433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/InertialSensors.2014.7049479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9918-3"},{"key":"ref14","first-page":"5450","article-title":"On the consistency analysis of A-SLAM for UAV navigation","volume":"9084","author":"oguz","year":"2014","journal-title":"Proc SPIE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364906065387"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2388780"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2012.11.012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908098412"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/s151229768"},{"key":"ref28","article-title":"Memory approaches to reinforcement learning in non-Markovian domains","author":"lin","year":"1992"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2017.05.012"},{"key":"ref27","first-page":"183","article-title":"Reinforcement learning with perceptual aliasing: The perceptual distinctions approach","author":"chrisman","year":"0","journal-title":"Proc Assoc Advance Artif Intell"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.sna.2012.11.017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2016.7505408"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2432455"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2238265"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354053"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907839"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2243480"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2014.6842265"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7148\/2015-0499"},{"key":"ref22","first-page":"1","article-title":"Visual odometry: Autonomous UAV navigation using optic flow and stereo","author":"strydom","year":"0","journal-title":"Australas Conf Robot Autom"},{"key":"ref21","article-title":"Visual based navigation for power line inspection by using virtual environments","volume":"9406","author":"cer\u00f3n","year":"0","journal-title":"Proc SPIE"},{"key":"ref42","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.009"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf on Learning Rep"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2017.8309082"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2016.7838739"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/8667487\/08600371.pdf?arnumber=8600371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T16:56:54Z","timestamp":1657731414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8600371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":42,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2018.2890773","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3]]}}}