{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:15Z","timestamp":1783542495785,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62403358"],"award-info":[{"award-number":["62403358"]}],"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":["62333017"],"award-info":[{"award-number":["62333017"]}],"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":["62233013"],"award-info":[{"award-number":["62233013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3703136","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:50:36Z","timestamp":1781553036000},"page":"11824-11839","source":"Crossref","is-referenced-by-count":0,"title":["KinematicRL: A Sim-to-Real Reinforcement Learning Framework for Social Navigation With Kinodynamic Feasibility"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3382-8474","authenticated-orcid":false,"given":"Zhiming","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9104-9430","authenticated-orcid":false,"given":"Haodong","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7543-0855","authenticated-orcid":false,"given":"Chengju","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5644-1188","authenticated-orcid":false,"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6804-3539","authenticated-orcid":false,"given":"Chenpeng","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160660"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3322093"},{"key":"ref7","first-page":"420","article-title":"Combining optimal control and learning for visual navigation in novel environments","volume-title":"Proc. Conf. Robot Learn.","author":"Bansal"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068662"},{"key":"ref9","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Anderson"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3213604"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561462"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611322"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3420353"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5652073"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ACC60939.2024.10644548"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ACC60939.2024.10644678"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561647"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341540"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092685"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341689"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref26","article-title":"Understanding domain randomization for sim-to-real transfer","author":"Chen","year":"2022","journal-title":"arXiv:2110.03239"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3234815"},{"key":"ref29","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parisotto"},{"key":"ref30","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2018","journal-title":"arXiv:1707.03141"},{"key":"ref31","first-page":"4425","article-title":"Improving transformer optimization through better initialization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref33","volume-title":"Modeling Purposeful Adaptive Behavior With the Principle of Maximum Causal Entropy","author":"Ziebart","year":"2010"},{"key":"ref34","first-page":"1","article-title":"Guided policy search","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Levine"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66723-8_19"},{"key":"ref36","first-page":"1259","article-title":"A divergence minimization perspective on imitation learning methods","volume-title":"Proc. Conf. Robot Learn.","author":"Ghasemipour"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref38","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref39","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref42","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"issue":"268","key":"ref43","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561948"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246134"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.059"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00374"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11563514.pdf?arnumber=11563514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:54Z","timestamp":1783539954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11563514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3703136","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}