{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:03:50Z","timestamp":1775325830269,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"A*STAR AME Young Individual Research","award":["A2084c0156"],"award-info":[{"award-number":["A2084c0156"]}]},{"name":"MTC Individual Research","award":["M22K2c0079"],"award-info":[{"award-number":["M22K2c0079"]}]},{"name":"ANR-NRF","award":["NRF2021-NRF-ANR003 HM Science"],"award-info":[{"award-number":["NRF2021-NRF-ANR003 HM Science"]}]},{"name":"SUG-NAP Grant of Nanyang Technological University, Singapore"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3314762","type":"journal-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T17:35:30Z","timestamp":1694626530000},"page":"14745-14759","source":"Crossref","is-referenced-by-count":86,"title":["Human-Guided Reinforcement Learning With Sim-to-Real Transfer for Autonomous Navigation"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7336-4492","authenticated-orcid":false,"given":"Jingda","family":"Wu","sequence":"first","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7199-2736","authenticated-orcid":false,"given":"Yanxin","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1545-2793","authenticated-orcid":false,"given":"Haohan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1592-7215","authenticated-orcid":false,"given":"Zhiyu","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6897-4512","authenticated-orcid":false,"given":"Chen","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2603528"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2972281"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2892489"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027983"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980479"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2017.2739706"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3167688"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3097435"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3057424"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3070514"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3185159"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.05.017"},{"key":"ref13","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3203974"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16975"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888918000292"},{"key":"ref17","first-page":"2067","article-title":"Trial without error: Towards safe reinforcement learning via human intervention","volume-title":"Proc. Int. Found. Auton. Agents Multiagent Syst.","author":"Saunders"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9921872"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref20","first-page":"1","article-title":"Making efficient use of demonstrations to solve hard exploration problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gulcehre"},{"key":"ref21","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref24","first-page":"410","article-title":"Intervention aided reinforcement learning for safe and practical policy optimization in navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref25","first-page":"1","article-title":"Efficient learning of safe driving policy via human-AI copilot optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3142822"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827073"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3177685"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/s18113650"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2928820"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49997.2022.9926582"},{"key":"ref32","article-title":"ModEL: A modularized end-to-end reinforcement learning framework for autonomous driving","author":"Wang","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/app12147194"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.102"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.091"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3209154"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3078353"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref41","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref42","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. 16th Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref43","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.11.007"},{"key":"ref46","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295387"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10250993.pdf?arnumber=10250993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T01:48:47Z","timestamp":1709344127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10250993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":47,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3314762","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}