{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T09:39:34Z","timestamp":1776505174896,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341647","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T14:49:56Z","timestamp":1615819796000},"page":"2235-2242","source":"Crossref","is-referenced-by-count":39,"title":["Learning hierarchical behavior and motion planning for autonomous driving"],"prefix":"10.1109","author":[{"given":"Jingke","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Dongkun","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yezhou","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Rong","family":"Xiong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16)"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref31","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref34","article-title":"Rethinking self-driving: Multi-task knowledge for better generalization and accident explanation ability","author":"li","year":"2018"},{"key":"ref10","article-title":"Sumo– simulation of urban mobility: an overview","author":"behrisch","year":"2011","journal-title":"Proceedings of SIMUL 2011 The Third International Conference on Advances in System Simulation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20147"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20258"},{"key":"ref14","article-title":"Baidu apollo em motion planner","author":"fan","year":"2018"},{"key":"ref15","first-page":"2722","article-title":"Deepdriving: Learning affordance for direct perception in autonomous driving","author":"chen","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref16","article-title":"Agile autonomous driving using end-to-end deep imitation learning","author":"pan","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref18","article-title":"Deep reinforcement learning for autonomous driving","author":"wang","year":"2018"},{"key":"ref19","article-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"sallab","year":"2016"},{"key":"ref28","article-title":"Conditional affordance learning for driving in urban environments","author":"sauer","year":"2018"},{"key":"ref4","first-page":"584","article-title":"Cirl: Controllable imitative reinforcement learning for vision-based self-driving","author":"liang","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref6","article-title":"Tactical decision making for lane changing with deep reinforcement learning","author":"mukadam","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.64"},{"key":"ref8","article-title":"Safe, multiagent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016"},{"key":"ref7","article-title":"Elements of effective deep reinforcement learning towards tactical driving decision making","author":"liu","year":"2018"},{"key":"ref2","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref9","article-title":"Carla: An open urban driving simulator","author":"dosovitskiy","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref20","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref21","article-title":"Learning by cheating","author":"chen","year":"2019"},{"key":"ref24","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref26","article-title":"Playing atari games with deep reinforcement learning and human checkpoint replay","author":"hosu","year":"2016"},{"key":"ref25","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341647.pdf?arnumber=9341647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T05:17:08Z","timestamp":1698038228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341647","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}