{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T19:19:46Z","timestamp":1785957586326,"version":"3.56.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF- 2019R1F1A1060525"],"award-info":[{"award-number":["NRF- 2019R1F1A1060525"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2020R1F1A1074843"],"award-info":[{"award-number":["2020R1F1A1074843"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/tvt.2021.3102589","type":"journal-article","created":{"date-parts":[[2021,8,5]],"date-time":"2021-08-05T20:16:11Z","timestamp":1628194571000},"page":"9725-9740","source":"Crossref","is-referenced-by-count":95,"title":["Energy-Efficient Online Path Planning of Multiple Drones Using Reinforcement Learning"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5359-4768","authenticated-orcid":false,"given":"Dooyoung","family":"Hong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7477-7806","authenticated-orcid":false,"given":"Seonhoon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3054-563X","authenticated-orcid":false,"given":"Young Hoo","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8056-744X","authenticated-orcid":false,"given":"Donkyu","family":"Baek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7697-0500","authenticated-orcid":false,"given":"Jaemin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3288-8174","authenticated-orcid":false,"given":"Naehyuck","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2017.2749181"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref33","year":"0","journal-title":"DJI M600 Pro Specs Dji Official Website"},{"key":"ref32","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","article-title":"Intel Realsense d455 Official Website","year":"0"},{"key":"ref30","first-page":"18","article-title":"Optimization of energy consumption for quadrotor UAV","author":"fouad","year":"2017","journal-title":"Proc Int Micro Air Veh Conf Flight Competition"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3_14","article-title":"Game theory and multi-agent reinforcement learning","author":"nowe","year":"2012","journal-title":"Adaptation Learning and Optimization"},{"key":"ref36","first-page":"4572","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc 30th Int Conf Neural Inform Process Syst"},{"key":"ref35","first-page":"2052","author":"fujimoto","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref34","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020","journal-title":"CoRR"},{"key":"ref10","first-page":"1444","article-title":"UAV coverage path planning under varying power constraints using deep reinforcement learning","author":"theile","year":"2020","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jweia.2020.104378"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.3390\/drones3030072","article-title":"Deep reinforcement learning for drone delivery","volume":"3","author":"mu\u00f1oz","year":"2019","journal-title":"Drones"},{"key":"ref12","first-page":"1995","author":"wang","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CoDIT.2019.8820322"},{"key":"ref14","first-page":"29","article-title":"Deep recurrent q-learning for partially observable MDPS","author":"hausknecht","year":"2015","journal-title":"Proc AAAI Fall Symp"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2954952"},{"key":"ref16","first-page":"1057","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref17","first-page":"1008","author":"v","year":"1999","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref18","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref19","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc 31th Int Conf Mach Learn"},{"key":"ref28","first-page":"1152","article-title":"Task and path planning for multi-agent pickup and delivery","author":"liu","year":"2019","journal-title":"Proc 18th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3040537"},{"key":"ref27","first-page":"131","article-title":"Multi-agent path finding for UAV traffic management","author":"ho","year":"2019","journal-title":"Proc 18th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref3","first-page":"58","article-title":"A comparative study on using brushless DC motor six-switch and four-switch inverter for UAV propulsion system","author":"elkerdany","year":"2020","journal-title":"Proc 12th Int Conf Elect Eng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2017.7991310"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref8","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref7","article-title":"Reinforcement learning for robots using neural networks","author":"lin","year":"1992"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3014411"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/M2VIP.2018.8600838"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/EPEPEMC.2014.6980715"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9181245"},{"key":"ref22","article-title":"Siemens Star-Ccm Official Website","year":"0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2019.8832593"},{"key":"ref24","first-page":"599","article-title":"Dijkstra's algorithm revisited: The dynamic programming connexion","volume":"35","author":"sniedovich","year":"2006","journal-title":"Control Cybern"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref25","article-title":"Rapidly-exploring random trees: A new tool for path planning","author":"lavalle","year":"1998","journal-title":"A Research Report"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/9576661\/09508149.pdf?arnumber=9508149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:48:38Z","timestamp":1652194118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9508149\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":40,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2021.3102589","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}