{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:22:52Z","timestamp":1740100972437,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["Z201100006820046"],"award-info":[{"award-number":["Z201100006820046"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772373"],"award-info":[{"award-number":["61772373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892236","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"01-08","source":"Crossref","is-referenced-by-count":0,"title":["Safety-based Reinforcement Learning Longitudinal Decision for Autonomous Driving in Crosswalk Scenarios"],"prefix":"10.1109","author":[{"given":"Fangzhou","family":"Xiong","sequence":"first","affiliation":[{"name":"Meituan,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongchun","family":"Ren","sequence":"additional","affiliation":[{"name":"Meituan,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyu","family":"Fan","sequence":"additional","affiliation":[{"name":"Wenzhou University,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuguang","family":"Ding","sequence":"additional","affiliation":[{"name":"Meituan,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref11","article-title":"Survey of deep reinforcement learning for motion planning of autonomous vehicles","author":"aradi","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ITSC.2018.8569568"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TITS.2019.2942050"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TITS.2019.2913998"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1103\/PhysRevE.62.1805"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/IV47402.2020.9304668"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.3141\/1999-10"},{"key":"ref18","article-title":"Amortized q-learning with model-based action proposals for autonomous driving on highways","author":"mirchevska","year":"2020","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1098\/rsta.2010.0084"},{"key":"ref4","article-title":"A survey of deep rl and il for autonomous driving policy learning","author":"zhu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref27","first-page":"16","article-title":"Smarts: An open-source scalable multi-agent rl training school for autonomous driving","volume":"155","author":"zhou","year":"0","journal-title":"Proceedings of the 2020 Conference on Robot Learning ser Proceedings of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICRA48506.2021.9561195"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TITS.2020.3036984"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/IVS.2018.8500400"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1126\/science.aaa8415"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1002\/rob.20255"},{"key":"ref2","article-title":"Interpretable end-to-end urban autonomous driving with latent deep reinforcement learning","author":"chen","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TSMC.2018.2800040"},{"key":"ref1","article-title":"Cooperative adaptive cruise control with robustness against communication delay: An approach in the space domain","author":"zhang","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref20","article-title":"Saint-acc: Safety-aware intelligent adaptive cruise control for autonomous vehicles using deep reinforcement learning","author":"das","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Safe multi-agent reinforcement learning via shielding","author":"eisayed-aly","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref21","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garcia","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","article-title":"Urban driving with multi-objective deep reinforcement learning","author":"li","year":"2018","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref26","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892236.pdf?arnumber=9892236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:57:08Z","timestamp":1667516228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892236","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}