{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T11:29:26Z","timestamp":1768735766692,"version":"3.49.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2016YFC1300205"],"award-info":[{"award-number":["2016YFC1300205"]}]},{"name":"National Key Research and Development Program of China","award":["2017YFB1301100"],"award-info":[{"award-number":["2017YFB1301100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572060"],"award-info":[{"award-number":["61572060"]}],"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":["61772060"],"award-info":[{"award-number":["61772060"]}],"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":["61728201"],"award-info":[{"award-number":["61728201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Education and Research Network (CERNET) Innovation Project","award":["NGII20170315"],"award-info":[{"award-number":["NGII20170315"]}]},{"name":"China Education and Research Network (CERNET) Innovation Project","award":["NGII20160316"],"award-info":[{"award-number":["NGII20160316"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tits.2019.2960872","type":"journal-article","created":{"date-parts":[[2019,12,31]],"date-time":"2019-12-31T21:02:13Z","timestamp":1577826133000},"page":"808-820","source":"Crossref","is-referenced-by-count":24,"title":["ReinforcementDriving: Exploring Trajectories and Navigation for Autonomous Vehicles"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4973-1571","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"first","affiliation":[]},{"given":"Fei","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3946-5107","authenticated-orcid":false,"given":"Jianwei","family":"Niu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7599-612X","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"42","article-title":"Actor–critic reinforcement learning for autonomous control of unmanned ground vehicles","volume":"354","author":"xu","year":"2016","journal-title":"Sci Robot"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225830"},{"key":"ref33","first-page":"1","article-title":"OpenAI gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref32","year":"2015","journal-title":"pyglet"},{"key":"ref31","year":"2000","journal-title":"Pygame"},{"key":"ref30","article-title":"Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst","author":"bansal","year":"2018","journal-title":"arXiv 1812 03079"},{"key":"ref37","first-page":"2061","article-title":"A real-time motion planner with trajectory optimization for autonomous vehicles","author":"xu","year":"2012","journal-title":"Proc IEEE Int Conf Robot Automat"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.2012116"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2005.858622"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2018.00035"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995727"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref13","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref14","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Int Conf Mach Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref16","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn ICML"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn ICML"},{"key":"ref18","first-page":"39:1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref19","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn ICML"},{"key":"ref28","article-title":"Learning to drive in a day","author":"kendall","year":"2018","journal-title":"arXiv 1807 00412"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2905","DOI":"10.3390\/s18092905","article-title":"Intelligent land-vehicle model transfer trajectory planning method based on deep reinforcement learning","volume":"18","author":"yu","year":"2018","journal-title":"SENSORS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","author":"lau","year":"2016","journal-title":"Ddpg Keras Torcs"},{"key":"ref29","article-title":"Learning deep neural network control policies for agile off-road autonomous driving","author":"pan","year":"2017","journal-title":"Proc NIPS Deep Rienforcement Learn Symp"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925881"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2463372.2463509"},{"key":"ref7","author":"jung","year":"2017","journal-title":"Self-Driving Truck"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn ICML"},{"key":"ref22","article-title":"A survey of deep network solutions for learning control in robotics: From reinforcement to imitation","author":"tai","year":"2016","journal-title":"arXiv 1612 07139"},{"key":"ref21","first-page":"1","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref24","article-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"sallab","year":"2016","journal-title":"arXiv 1612 04340"},{"key":"ref23","first-page":"1","article-title":"Simulated car racing championship: Competition software manual","volume":"abs 1304 1672","author":"loiacono","year":"2013","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FBIT.2007.37"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(95)00009-5"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9345541\/08946763.pdf?arnumber=8946763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T15:19:47Z","timestamp":1695568787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8946763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":40,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tits.2019.2960872","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}