{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:44:30Z","timestamp":1781797470997,"version":"3.54.5"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ontario Centers of Excellence","award":["27481"],"award-info":[{"award-number":["27481"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2974695","type":"journal-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T21:23:37Z","timestamp":1582061017000},"page":"3221-3226","source":"Crossref","is-referenced-by-count":129,"title":["Multi-Agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7289-8839","authenticated-orcid":false,"given":"Samaneh Hosseini","family":"Semnani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2835-4487","authenticated-orcid":false,"given":"Hugh","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9377-6745","authenticated-orcid":false,"given":"Michael","family":"Everett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4118-3918","authenticated-orcid":false,"given":"Anton","family":"de Ruiter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8576-1930","authenticated-orcid":false,"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Force-based algorithm for motion planning of large agent teams","author":"semnani","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2656241"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5652073"},{"key":"ref13","first-page":"739","article-title":"Off-road obstacle avoidance through end-to-end learning","author":"muller","year":"0","journal-title":"Proc Adv Neu Inf Proc Sys"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1998.680648"},{"key":"ref19","article-title":"Pearl: Preference appraisal reinforcement learning for motion planning","author":"faust","year":"2018"},{"key":"ref28","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"0","journal-title":"Proc USENIX Symp on Operating System Design and Implementation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385823"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.864190"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917741532"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref29","article-title":"Java implementation of orca collisionavoidance algorithm","author":"janovsky","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202165"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_15"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980408"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2593448"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2013.2245612"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2890572"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref21","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a GPU","author":"babaeizadeh","year":"2017","journal-title":"Learning Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2328659"},{"key":"ref25","article-title":"cadrl-ros (collision avoidance with deep rl)","author":"everett","year":"2011"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/09001226.pdf?arnumber=9001226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:32:36Z","timestamp":1651080756000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9001226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":29,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2974695","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}