{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T01:02:37Z","timestamp":1779238957608,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008868","name":"Jiangsu Province Frontier Leading Technology Basic Research Project","doi-asserted-by":"publisher","award":["BK20222013"],"award-info":[{"award-number":["BK20222013"]}],"id":[{"id":"10.13039\/501100008868","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62231015"],"award-info":[{"award-number":["62231015"]}],"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":["62222107"],"award-info":[{"award-number":["62222107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,6,1]]},"DOI":"10.1109\/jiot.2025.3532164","type":"journal-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:59:33Z","timestamp":1737399573000},"page":"15926-15938","source":"Crossref","is-referenced-by-count":3,"title":["AAV Visual Navigation in the Large-Scale Outdoor Environment: A Semantic-Map-Based Cognitive Escape Reinforcement Learning Method"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9168-1221","authenticated-orcid":false,"given":"Shijin","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6880-6244","authenticated-orcid":false,"given":"Fuhui","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9521-5084","authenticated-orcid":false,"given":"Qihui","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2018.1800160"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3176903"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2968343"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/drones7020089"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/10095020.2017.1420509"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/robotics11010024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace9020048"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICARA56516.2023.10125712"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00284"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3277598"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0102-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3257291"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2994002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10796-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161059"},{"key":"ref17","first-page":"18733","article-title":"Learning in POMDPs is sample-efficient with hindsight observability","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lee"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2973193"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"ref20","first-page":"578","article-title":"Provably efficient reinforcement learning in partially observable dynamical systems","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Uehara"},{"key":"ref21","first-page":"1458","article-title":"Learning in observable POMDPs, without computationally intractable oracles","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Golowich"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-2661516\/v1","volume-title":"Cognitive Escape Reinforcement Learning for Complex Decision Making","author":"Wu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3063188"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref25","first-page":"1","article-title":"Diversity-driven exploration strategy for deep reinforcement learning","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Hong"},{"key":"ref26","first-page":"5175","article-title":"When is partially observable reinforcement learning not scary?","volume-title":"Proc. Conf. Learn. Theory","author":"Liu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","first-page":"1","article-title":"Memory augmented control networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Khan"},{"key":"ref29","first-page":"2332","article-title":"An empirical exploration of recurrent network architectures","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","author":"Jozefowicz"},{"key":"ref30","article-title":"Learning to navigate in complex environments","author":"Mirowski","year":"2017","journal-title":"arXiv:1611.03673"},{"key":"ref31","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Mnih"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967677"},{"key":"ref33","first-page":"2347","article-title":"On the difficulty of training recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Pascanu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref35","first-page":"2827","article-title":"Neural episodic control","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Pritzel"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812027"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17457"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref41","first-page":"8622","article-title":"Adversarial intrinsic motivation for reinforcement learning","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Durugkar"},{"key":"ref42","first-page":"1","article-title":"Adversarially guided actor-critic","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Flet-Berliac"},{"key":"ref43","first-page":"1","article-title":"Episodic curiosity through reachability","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Savinov"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20743"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref46","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Wang"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11008454\/10847926.pdf?arnumber=10847926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:42:15Z","timestamp":1747849335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10847926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,1]]},"references-count":46,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3532164","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,1]]}}}