{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T05:20:24Z","timestamp":1773465624863,"version":"3.50.1"},"reference-count":46,"publisher":"Informa UK Limited","issue":"8","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2022,4,18]]},"DOI":"10.1080\/01691864.2022.2043184","type":"journal-article","created":{"date-parts":[[2022,3,8]],"date-time":"2022-03-08T19:18:21Z","timestamp":1646767101000},"page":"388-403","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":17,"title":["Socially aware robot navigation in crowds via deep reinforcement learning with resilient reward functions"],"prefix":"10.1080","volume":"36","author":[{"given":"Xiaojun","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Precision Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8586-4304","authenticated-orcid":false,"given":"Hanwool","family":"Woo","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8948-3592","authenticated-orcid":false,"given":"Angela","family":"Faragasso","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1280-069X","authenticated-orcid":false,"given":"Atsushi","family":"Yamashita","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9482-497X","authenticated-orcid":false,"given":"Hajime","family":"Asama","sequence":"additional","affiliation":[{"name":"Department of Precision Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2022,3,8]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2017.1365009"},{"key":"CIT0002","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"CIT0003","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"CIT0004","doi-asserted-by":"crossref","unstructured":"Van den Berg J, Lin M, Manocha D. Reciprocal velocity obstacles for real-time multi-agent navigation. 2008 IEEE international conference on robotics and automation; Pasadena, USA. IEEE; 2008. p.\u00a01928\u20131935.","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"CIT0005","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"CIT0006","doi-asserted-by":"crossref","unstructured":"Ferrer G, Garrell A, Sanfeliu A. Social-aware robot navigation in urban environments. 2013 European Conference on Mobile Robots; Barcelona, Spain. IEEE; 2013. p.\u00a0331\u2013336.","DOI":"10.1109\/ECMR.2013.6698863"},{"key":"CIT0007","doi-asserted-by":"crossref","unstructured":"Unhelkar VV, P\u00e9rez-D'Arpino C, Stirling L, et\u00a0al. Human\u2013robot co-navigation using anticipatory indicators of human walking motion. 2015 IEEE International Conference on Robotics and Automation (ICRA); Seattle, USA. IEEE; 2015. p.\u00a06183\u20136190.","DOI":"10.1109\/ICRA.2015.7140067"},{"key":"CIT0008","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914555543"},{"key":"CIT0009","doi-asserted-by":"crossref","unstructured":"Trautman P, Krause A. Unfreezing the robot: navigation in dense, interacting crowds. 2010 IEEE\/RSJ International Conference on Intelligent Robots and Systems; Taipei, Taiwan. IEEE; 2010. p.\u00a0797\u2013803.","DOI":"10.1109\/IROS.2010.5654369"},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696576"},{"key":"CIT0011","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907734"},{"key":"CIT0012","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759200"},{"key":"CIT0013","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"CIT0014","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"CIT0015","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"CIT0016","doi-asserted-by":"crossref","unstructured":"Chen C, Liu Y, Kreiss S, et\u00a0al. Crowd\u2013robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning. 2019 International Conference on Robotics and Automation (ICRA); Montreal, Canada. IEEE; 2019. p.\u00a06015\u20136022.","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"CIT0017","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972868"},{"key":"CIT0018","unstructured":"Brscic D, Kanda T, Ikeda T, et\u00a0al. Datasets from the ATC shopping center; 2013 [cited 2021 May 5]. Available from: https:\/\/irc.atr.jp\/crest2010_HRI\/ATC_dataset\/"},{"key":"CIT0019","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-014-0251-1"},{"key":"CIT0020","doi-asserted-by":"publisher","DOI":"10.1037\/h0081182"},{"key":"CIT0021","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(1986)112:3(229)"},{"key":"CIT0022","volume-title":"The hidden dimension","volume":"609","author":"Hall ET.","year":"1966"},{"key":"CIT0023","doi-asserted-by":"publisher","DOI":"10.1007\/BF02170028"},{"key":"CIT0024","doi-asserted-by":"publisher","DOI":"10.1007\/11861201_57"},{"key":"CIT0025","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2006.314436"},{"key":"CIT0026","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206628"},{"key":"CIT0027","doi-asserted-by":"crossref","unstructured":"Tsai CE, Oh J. A generative approach for socially compliant navigation. 2020 IEEE International Conference on Robotics and Automation (ICRA); Paris, France. IEEE; 2020. p.\u00a02160\u20132166.","DOI":"10.1109\/ICRA40945.2020.9197497"},{"key":"CIT0028","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"CIT0029","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_33"},{"key":"CIT0030","doi-asserted-by":"publisher","DOI":"10.1177\/0361198118786641"},{"key":"CIT0031","doi-asserted-by":"publisher","DOI":"10.1145\/1401132.1401207"},{"key":"CIT0032","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-016-9584-y"},{"key":"CIT0033","doi-asserted-by":"crossref","unstructured":"Trautman P, Ma J, Murray RM, et\u00a0al. Robot navigation in dense human crowds: the case for cooperation. 2013 IEEE International Conference on Robotics and Automation; Karlsruhe, German. IEEE; 2013. p.\u00a02153\u20132160.","DOI":"10.1109\/ICRA.2013.6630866"},{"key":"CIT0034","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263686"},{"key":"CIT0035","doi-asserted-by":"crossref","unstructured":"Tai L, Zhang J, Liu M, et\u00a0al. Socially compliant navigation through raw depth inputs with generative adversarial imitation learning. 2018 IEEE International Conference on Robotics and Automation (ICRA); Brisbane, Australia. IEEE; 2018. p.\u00a01111\u20131117.","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"CIT0036","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651371"},{"key":"CIT0037","doi-asserted-by":"crossref","unstructured":"Liu Y, Xu A, Chen Z. Map-based deep imitation learning for obstacle avoidance. 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); Madrid, Spain. IEEE; 2018. p.\u00a08644\u20138649.","DOI":"10.1109\/IROS.2018.8593683"},{"key":"CIT0038","doi-asserted-by":"crossref","unstructured":"Pfeiffer M, Schwesinger U, Sommer H, et\u00a0al. Predicting actions to act predictably: cooperative partial motion planning with maximum entropy models. 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); Daejeon, Korea. IEEE; 2016. p.\u00a02096\u20132101.","DOI":"10.1109\/IROS.2016.7759329"},{"key":"CIT0039","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"CIT0040","doi-asserted-by":"crossref","unstructured":"Long P, Fan T, Liao X, et\u00a0al. Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning. 2018 IEEE International Conference on Robotics and Automation (ICRA); Brisbane, Australia. IEEE; 2018. p.\u00a06252\u20136259.","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"CIT0041","doi-asserted-by":"crossref","unstructured":"Tai L, Paolo G, Liu M. Virtual-to-real deep reinforcement learning: continuous control of mobile robots for mapless navigation. 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS); Vancouver, Canada. IEEE; 2017. p.\u00a031\u201336.","DOI":"10.1109\/IROS.2017.8202134"},{"key":"CIT0042","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2013.2283945"},{"key":"CIT0043","doi-asserted-by":"crossref","unstructured":"Lample G, Chaplot DS. Playing fps games with deep reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence; San Francisco, USA. Vol.\u00a031; 2017.","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"CIT0044","unstructured":"Botteghi N, Sirmacek B, Mustafa KA, et\u00a0al. On reward shaping for mobile robot navigation: a reinforcement learning and slam based approach. Preprint 2020. Available from: arxiv:2002.04109"},{"key":"CIT0045","unstructured":"Paszke A, Gross S, Massa F, et\u00a0al. Pytorch: an imperative style, high-performance deep learning library. Preprint 2019. Available from: arxiv:1912.01703"},{"key":"CIT0046","unstructured":"Brockman G, Cheung V, Pettersson L, et\u00a0al. Openai gym. Preprint 2016. Available from: arxiv:1606.01540"}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2022.2043184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T16:48:28Z","timestamp":1674924508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2022.2043184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,8]]},"references-count":46,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,4,18]]}},"alternative-id":["10.1080\/01691864.2022.2043184"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2022.2043184","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,8]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2021-06-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-20","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}