{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T14:16:46Z","timestamp":1784989006053,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100002427","name":"Ford Motor Company","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002427","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008536","name":"Amazon Web Services","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008536","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3050338","type":"journal-article","created":{"date-parts":[[2021,1,9]],"date-time":"2021-01-09T22:37:00Z","timestamp":1610231820000},"page":"10357-10377","source":"Crossref","is-referenced-by-count":202,"title":["Collision Avoidance in Pedestrian-Rich Environments With Deep Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9377-6745","authenticated-orcid":false,"given":"Michael","family":"Everett","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu Fan","family":"Chen","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":"ref39","author":"lau","year":"2019","journal-title":"Rl-Collision-Avoidance"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref33","article-title":"Emergent tool use from multi-agent autocurricula","author":"baker","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759329"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0310-2"},{"key":"ref30","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"arXiv 1604 07316 [cs]"},{"key":"ref37","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"Proc OSDI"},{"key":"ref36","article-title":"Understanding LSTM networks","author":"olah","year":"2015","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref34","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref40","year":"2019","journal-title":"Intel drones light up the sky"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref12","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/37.845037"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref28","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2013.6698863"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2120810"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_15"},{"key":"ref29","first-page":"1","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-19457-3_1","article-title":"Reciprocal n-body collision avoidance","author":"van den berg","year":"2011","journal-title":"Robotics Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630866"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2012.VIII.025"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631026"},{"key":"ref46","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980306"},{"key":"ref45","first-page":"449","article-title":"Dynamic clustering via asymptotics of the dependent Dirichlet process mixture","author":"campbell","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","article-title":"Robot designed for socially acceptable navigation","author":"everett","year":"2017"},{"key":"ref22","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759357"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-013-9334-3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/267658.267738"},{"key":"ref24","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","year":"2019","journal-title":"Airbus Commercial Aircraft Formation Flight 50-Year Anniversary"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2514\/6.2015-0643"},{"key":"ref26","article-title":"Crossmodal attentive skill learner","author":"omidshafiei","year":"2017","journal-title":"arXiv 1711 10314"},{"key":"ref43","year":"2003","journal-title":"Finding Nemo (School of Fish Scene)"},{"key":"ref25","first-page":"1","article-title":"Reinforcement learning thorugh asynchronous advantage actor-critic on a GPU","author":"babaeizadeh","year":"2017","journal-title":"Proc ICLR"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09317723.pdf?arnumber=9317723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:05Z","timestamp":1639770965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9317723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3050338","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}