{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:36:57Z","timestamp":1784644617647,"version":"3.55.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403240"],"award-info":[{"award-number":["62403240"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241396"],"award-info":[{"award-number":["BK20241396"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tits.2025.3557191","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T14:25:10Z","timestamp":1750861510000},"page":"12358-12371","source":"Crossref","is-referenced-by-count":4,"title":["Selective Imitation Enhanced Deep Reinforcement Learning for AAV Navigation and Obstacle Avoidance With Sparse Rewards"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9995-4239","authenticated-orcid":false,"given":"Chao","family":"Yan","sequence":"first","affiliation":[{"name":"College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihao","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0023-6569","authenticated-orcid":false,"given":"Yuna","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1525-6231","authenticated-orcid":false,"given":"Xiaojia","family":"Xiang","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7158-8575","authenticated-orcid":false,"given":"Mou","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3342174"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3094207"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3343713"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3505929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3375893"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2022.3216989"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2022.108064"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108194"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3218855"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3327753"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10794-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2973193"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/927"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161492"},{"key":"ref17","first-page":"465","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Goecks"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110604"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711835"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3384992"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3361494"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.113811"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3464510"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2024.09.001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3049681"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2023.100107"},{"key":"ref27","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3245124"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3330703"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020564024509"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3331886"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat3536"},{"key":"ref33","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3240671"},{"key":"ref36","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref37","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv:1707.08817"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103594"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MMAR.2017.8046794"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11121550\/11051094.pdf?arnumber=11051094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:51:54Z","timestamp":1770411114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11051094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":39,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3557191","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}