{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:50:56Z","timestamp":1771955456651,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018594","name":"Central University Basic Research Fund of China","doi-asserted-by":"publisher","award":["YWF-22-L-539"],"award-info":[{"award-number":["YWF-22-L-539"]}],"id":[{"id":"10.13039\/501100018594","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tai.2023.3283488","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T13:45:31Z","timestamp":1686145531000},"page":"1263-1276","source":"Crossref","is-referenced-by-count":9,"title":["Learning Visual Representation for Autonomous Drone Navigation via a Contrastive World Model"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9873-156X","authenticated-orcid":false,"given":"Jiang","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0088-8217","authenticated-orcid":false,"given":"Yibo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}]},{"given":"Zhihao","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}]},{"given":"Ningjun","family":"Liu","sequence":"additional","affiliation":[{"name":"Unmanned System Research Institute, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2912-4256","authenticated-orcid":false,"given":"Kun","family":"Wu","sequence":"additional","affiliation":[{"name":"Flying College, Beihang University, Beijing, China"}]},{"given":"Yingxun","family":"Wang","sequence":"additional","affiliation":[{"name":"Unmanned System Research Institute, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3053511"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref5","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341049"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982241"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068639"},{"key":"ref9","first-page":"9465","article-title":"RRL: Resnet as representation for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shah","year":"2021"},{"key":"ref10","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Proc. Conf. Robot Learn.","author":"Radosavovic","year":"2023"},{"key":"ref11","first-page":"17359","article-title":"The unsurprising effectiveness of pre-trained vision models for control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parisi","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0264471"},{"key":"ref13","first-page":"26345","article-title":"Which mutual-information representation learning objectives are sufficient for control?","volume":"34","author":"Rakelly","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31635-3_22"},{"key":"ref17","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hafner","year":"2020"},{"key":"ref18","first-page":"959","article-title":"Contrastive variational reinforcement learning for complex observations","volume-title":"Proc. 2020 Conf. Robot Learn.","author":"Ma","year":"2021"},{"key":"ref19","article-title":"CarNet: A dynamic autoencoder for learning latent dynamics in autonomous driving tasks","author":"Pak","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560734"},{"key":"ref21","first-page":"4956","article-title":"Dreamerpro: Reconstruction-free model-based reinforcement learning with prototypical representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deng","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982045"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160563"},{"key":"ref25","first-page":"1023","article-title":"Acting optimally in partially observable stochastic domains","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"94","author":"Cassandra","year":"1994"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/2200000089"},{"key":"ref27","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hafner","year":"2019"},{"key":"ref28","article-title":"Contrastive learning with hard negative samples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Robinson","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref31","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kostrikov","year":"2020"},{"key":"ref32","first-page":"4214","article-title":"MUESLI: Combining improvements in policy optimization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Hessel","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28872-7_37"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref36","first-page":"177","article-title":"Airsim drone racing lab","volume-title":"Proc. Neural Inf. Process. Syst. Competition Demonstration Track","author":"Madaan","year":"2020"},{"key":"ref37","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke","year":"2021"},{"key":"ref38","article-title":"Neural predictive belief representations","author":"Guo","year":"2018"},{"key":"ref39","first-page":"133","article-title":"Deep drone racing: Learning agile flight in dynamic environments","volume-title":"Proc. Conf. Robot Learn.","author":"Kaufmann","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793631"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50115-4_1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"issue":"11","key":"ref44","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10478748\/10145773.pdf?arnumber=10145773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:57Z","timestamp":1755911337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10145773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":46,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tai.2023.3283488","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}