{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:23:05Z","timestamp":1774934585714,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"HKSAR General Research Fund","award":["HKU 11202119"],"award-info":[{"award-number":["HKU 11202119"]}]},{"name":"HKSAR General Research Fund","award":["11207818"],"award-info":[{"award-number":["11207818"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2974648","type":"journal-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T21:23:37Z","timestamp":1582061017000},"page":"3098-3105","source":"Crossref","is-referenced-by-count":120,"title":["A Two-Stage Reinforcement Learning Approach for Multi-UAV Collision Avoidance Under Imperfect Sensing"],"prefix":"10.1109","volume":"5","author":[{"given":"Dawei","family":"Wang","sequence":"first","affiliation":[]},{"given":"Tingxiang","family":"Fan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5487-6206","authenticated-orcid":false,"given":"Tao","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9003-2054","authenticated-orcid":false,"given":"Jia","family":"Pan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219961"},{"key":"ref32","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-19457-3_1","article-title":"Reciprocal n-body collision avoidance","author":"van den berg","year":"2011","journal-title":"Robotics Research"},{"key":"ref10","article-title":"Autonomous navigation of mavs in unknown cluttered environments","author":"c -mac\u00edas","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref14","article-title":"Fully distributed multi-robot collision avoidance via deep reinforcement learning for safe and efficient navigation in complex scenarios","author":"fan","year":"2018"},{"key":"ref15","article-title":"Deep reinforcement learning doesn't work yet","author":"irpan","year":"2018"},{"key":"ref16","first-page":"153","article-title":"The difficulty of training deep architectures and the effect of unsupervised pre-training","author":"erhan","year":"0","journal-title":"Proc Artif Intell Statist"},{"key":"ref17","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref18","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref28","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/11008941_27"},{"key":"ref27","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73424-6_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225009"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2002.1184270"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2013.2293148"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2275670"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2018.6043"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2018.6163"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.03.024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9819-5"},{"key":"ref22","article-title":"Teach-repeat-replan: A complete and robust system for aggressive flight in complex environments","author":"gao","year":"2019"},{"key":"ref21","first-page":"8","article-title":"Low cost GPS\/INS sensor fusion system for UAV navigation","volume":"2","author":"yoo","year":"0","journal-title":"Proc Digit Avionics Syst Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/35035023"},{"key":"ref26","article-title":"Learning decentralized controllers for robot swarms with graph neural networks","author":"tolstaya","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/09001167.pdf?arnumber=9001167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:32:49Z","timestamp":1651080769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9001167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":33,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2974648","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}