{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:28:07Z","timestamp":1760171287058,"version":"3.37.3"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Research Foundation (NRF), Singapore"},{"name":"DSO National Laboratories"},{"name":"AI Singapore Program AISG","award":["AISG2-RP-2020-016"],"award-info":[{"award-number":["AISG2-RP-2020-016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/tro.2022.3210767","type":"journal-article","created":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:27:23Z","timestamp":1669854443000},"page":"998-1011","source":"Crossref","is-referenced-by-count":11,"title":["Closing the Planning\u2013Learning Loop With Application to Autonomous Driving"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1926-4842","authenticated-orcid":false,"given":"Panpan","family":"Cai","sequence":"first","affiliation":[{"name":"Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2309-4535","authenticated-orcid":false,"given":"David","family":"Hsu","sequence":"additional","affiliation":[{"name":"School of Computing and the Smart Systems Institute, National University of Singapore, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920937074"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197228"},{"year":"2017","key":"ref4","article-title":"Planet dump retrieved from https:\/\/planet.osm.org"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144501"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"issue":"1","key":"ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/02331880309257","article-title":"Bayesian filtering: From Kalman filters to particle filters, and beyond","volume":"182","author":"Chen","year":"2003","journal-title":"Statistics"},{"key":"ref8","first-page":"2164","article-title":"Monte-Carlo planning in large POMDPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Silver","year":"2010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5328"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139219"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967873"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793494"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s20174739"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852793"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/700"},{"key":"ref16","first-page":"4697","article-title":"QMDP-Net: Deep learning for planning under partial observability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karkus","year":"2017"},{"key":"ref17","article-title":"TreeQN and ATreeC: Differentiable tree-structured models for deep reinforcement learning","volume-title":"Proc. 6th Int. Conf. Learn. Representations, Conf. Track Proc.","volume":"6","author":"Farquhar","year":"2018"},{"key":"ref18","first-page":"1822","article-title":"Learning to search with MCTSnets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guez","year":"2018"},{"key":"ref19","first-page":"4732","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srinivas","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2022.06.001"},{"key":"ref21","first-page":"463","article-title":"Model-based reinforcement learning with value-targeted regression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ayoub","year":"2020"},{"key":"ref22","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hafner","year":"2019"},{"key":"ref23","first-page":"42","article-title":"Dynamics learning with cascaded variational inference for multi-step manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Fang","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196771"},{"key":"ref25","first-page":"420","article-title":"Combining optimal control and learning for visual navigation in novel environments","volume-title":"Proc. Conf. Robot Learn.","author":"Bansal","year":"2020"},{"key":"ref26","article-title":"MAGIC: Learning macro-actions for online POMDP planning using generator-critic","volume-title":"Proc. Robot.: Sci. Syst.","author":"Lee","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.018"},{"volume-title":"Introduction to Autonomous Mobile Robots","year":"2011","author":"Siegwart","key":"ref28"},{"issue":"6","key":"ref29","first-page":"33","article-title":"Pyramid methods in image processing","volume":"29","author":"Adelson","year":"1984","journal-title":"RCA Eng."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001"},{"key":"ref32","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref33","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Representations, Conf. Track Proc., Poster","author":"Lillicrap","year":"2016"},{"key":"ref34","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","year":"2018"},{"article-title":"Soft actor-critic for discrete action settings","year":"2019","author":"Christodoulou","key":"ref35"},{"issue":"384","key":"ref36","first-page":"24","article-title":"Near-miss determination through use of a scale of danger","volume-title":"Proc. 51st Annu. Meeting Highway Res. Board","author":"Hayward","year":"1972"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2013.6728533"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/664"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3182687"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.034"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793668"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/10092518\/09967016.pdf?arnumber=9967016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:03:03Z","timestamp":1706756583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9967016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":44,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tro.2022.3210767","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"type":"print","value":"1552-3098"},{"type":"electronic","value":"1941-0468"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}