{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T09:54:20Z","timestamp":1768038860178,"version":"3.49.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203252"],"award-info":[{"award-number":["62203252"]}],"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":["52205008"],"award-info":[{"award-number":["52205008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3268524","type":"journal-article","created":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T17:35:41Z","timestamp":1681925741000},"page":"66756-66766","source":"Crossref","is-referenced-by-count":9,"title":["Online Series-Parallel Reinforcement-Learning- Based Balancing Control for Reaction Wheel Bicycle Robots on a Curved Pavement"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8894-5700","authenticated-orcid":false,"given":"Xianjin","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7318-1899","authenticated-orcid":false,"given":"Yang","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6743-4327","authenticated-orcid":false,"given":"Qingyuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7163-345X","authenticated-orcid":false,"given":"Bin","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9107-6390","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/00423114.2015.1037313"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1729881417707170"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/su9050866"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2992792"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1049\/cth2.12199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2022.09.380"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5302\/J.ICROS.2012.18.6.532"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979841"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665347"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1995.525473"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.4271\/10-03-01-0004"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechmachtheory.2021.104643"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859392"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2020.102386"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3140885"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.1773"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1115\/1.4027852"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA52036.2021.9512587"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAS.2013.6703879"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14736\/kyb-2015-1-0173"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1642091"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.2004349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref27","first-page":"Alstr","volume-title":"Learning to Drive a Bicycle Using Reinforcement Learning and Shaping","author":"Randl\u00f8v AND p","year":"1998"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/sym11020290"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/01423312211037847"},{"key":"ref30","volume-title":"A deep reinforcement learning approach for robotic bicycle stabilization,","author":"Turakhia","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2020.02.017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tfuzz.2022.3227993"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2022.127759"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2022.107760"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11213495"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA49215.2020.9233833"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s12206-019-1239-4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2015.7418805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00145-5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CoDIT.2014.6996958"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.2983658"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2464080"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref45","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-021-06380-9"},{"key":"ref47","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref48","article-title":"Hierarchical reinforcement learning with hindsight","author":"Levy","year":"2018","journal-title":"arXiv:1805.08180"},{"key":"ref49","article-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017","journal-title":"arXiv:1712.00948"},{"key":"ref50","volume-title":"Simscape Model and Simulate Multidomain Physical Systems","author":"Documentation","year":"2022"},{"key":"ref51","volume-title":"Nonlinear MPC Controller","author":"Documentation","year":"2022"},{"key":"ref52","volume-title":"Simscape Multibody Contact Forces Library","author":"Miller","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20147"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-63519-3_5"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10105202.pdf?arnumber=10105202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:42:04Z","timestamp":1710380524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10105202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3268524","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}