{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:51:56Z","timestamp":1782762716959,"version":"3.54.5"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["T2350005"],"award-info":[{"award-number":["T2350005"]}],"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":["T2541041"],"award-info":[{"award-number":["T2541041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20210623091807023"],"award-info":[{"award-number":["ZDSYS20210623091807023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/lra.2026.3704013","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:45:22Z","timestamp":1781639122000},"page":"9343-9350","source":"Crossref","is-referenced-by-count":0,"title":["CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1085-9061","authenticated-orcid":false,"given":"Gelu","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electronics and Communication Engineering and Shenzhen Key Laboratory of Navigation and Communication Integration, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3705-9770","authenticated-orcid":false,"given":"Teng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering and Shenzhen Key Laboratory of Navigation and Communication Integration, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8036-4088","authenticated-orcid":false,"given":"Zhijie","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering and Shenzhen Key Laboratory of Navigation and Communication Integration, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9836-3984","authenticated-orcid":false,"given":"Junliang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering and Shenzhen Key Laboratory of Navigation and Communication Integration, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4052-1006","authenticated-orcid":false,"given":"Songyuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering and Shenzhen Key Laboratory of Navigation and Communication Integration, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4821-2638","authenticated-orcid":false,"given":"Xiangwei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering and Shenzhen Key Laboratory of Navigation and Communication Integration, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2024.3395575"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2962338"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2025.3572225"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574724001437"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2018-9244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11044-018-9614-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665347"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1424-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3136142"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2015.04.010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814124"},{"key":"ref12","first-page":"1186","article-title":"Isaac gym: High performance GPU based physics simulation for robot learning","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Makoviychuk","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2019.2901089"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.2004349"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564999"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385023310027"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106941"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3126904"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2023.11.032"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3064065"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3472348"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062303"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2007.1857"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564958"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3257681"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-023-09249-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_17"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11570239\/11568521.pdf?arnumber=11568521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:41:39Z","timestamp":1782762099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11568521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":30,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3704013","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}