{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:55:02Z","timestamp":1781110502268,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0117103"],"award-info":[{"award-number":["2022ZD0117103"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272364"],"award-info":[{"award-number":["62272364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Teaching Reform Project of Shaanxi Higher Continuing Education","award":["21XJZ004"],"award-info":[{"award-number":["21XJZ004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tiv.2023.3347531","type":"journal-article","created":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T19:46:39Z","timestamp":1703706399000},"page":"5543-5553","source":"Crossref","is-referenced-by-count":10,"title":["Deep Reinforcement Learning-Based Off-Road Path Planning via Low-Dimensional Simulation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0935-6735","authenticated-orcid":false,"given":"Xu","family":"Wang","sequence":"first","affiliation":[{"name":"Xi'an Key Laboratory of Big Data and Intelligent Vision, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6669-3933","authenticated-orcid":false,"given":"Erke","family":"Shang","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Dai","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6766-8310","authenticated-orcid":false,"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[{"name":"Xi'an Key Laboratory of Big Data and Intelligent Vision, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0421-595X","authenticated-orcid":false,"given":"Yiming","family":"Nie","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2019.04.011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561834"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2009.4983199"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3207346"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575880"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3312777"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8377"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"issue":"3","key":"ref9","first-page":"599","article-title":"Dijkstra\u2019s algorithm revisited: The dynamic programming connexion","volume":"35","author":"Sniedovich","year":"2006","journal-title":"Control Cybern."},{"key":"ref10","article-title":"Rapidly-exploring random trees: A new tool for path planning","author":"LaValle","year":"1998","journal-title":"Res. Rep."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102565"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/37.845037"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3317833"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s22207968"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2976560"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","first-page":"1","article-title":"Sharing knowledge in multi-task deep reinforcement learning","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"D\u2019Eramo","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.031"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161449"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3254579"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304721"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922100"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2021.01.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2023.3307409"},{"issue":"3.2","key":"ref28","first-page":"5","article-title":"Ros: An open-source robot operating system","volume":"3","author":"Quigley","year":"2009","journal-title":"Proc. IEEE Int. Conf. Robot. Automat. Workshop Open Source Softw."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3314762"},{"key":"ref30","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Proc. Conf. Robot. Learn.","author":"Dosovitskiy","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref35","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref37","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"key":"ref39","article-title":"Plan-based relaxed reward shaping for goal-directed tasks","author":"Schubert","year":"2021"},{"key":"ref40","article-title":"Shortest-path constrained reinforcement learning for sparse reward tasks","author":"Sohn","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811712"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref43","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"issue":"1","key":"ref45","first-page":"7382","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9889-4"},{"key":"ref47","first-page":"440","article-title":"Prioritized level replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274857\/11023975\/10375107.pdf?arnumber=10375107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T17:38:43Z","timestamp":1749145123000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10375107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":47,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2023.3347531","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}