{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:47:06Z","timestamp":1730270826037,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981645","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"9164-9171","source":"Crossref","is-referenced-by-count":1,"title":["SESNO: Sample Efficient Social Navigation from Observation"],"prefix":"10.1109","author":[{"given":"Bobak H.","family":"Baghi","sequence":"first","affiliation":[{"name":"Samsung Electronics SAIC-Montreal,Montreal,QC,Canada,H3A 3R2"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhisek","family":"Konar","sequence":"additional","affiliation":[{"name":"Samsung Electronics SAIC-Montreal,Montreal,QC,Canada,H3A 3R2"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francois","family":"Hogan","sequence":"additional","affiliation":[{"name":"Samsung Electronics SAIC-Montreal,Montreal,QC,Canada,H3A 3R2"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Jenkin","sequence":"additional","affiliation":[{"name":"Samsung Electronics SAIC-Montreal,Montreal,QC,Canada,H3A 3R2"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"Dudek","sequence":"additional","affiliation":[{"name":"Samsung Electronics SAIC-Montreal,Montreal,QC,Canada,H3A 3R2"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"575","article-title":"Modeling collision avoidance behavior for virtual humans","author":"Guy","year":"2010","journal-title":"AAMAS, Richland, SC"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1038\/nature14236"},{"key":"ref3","first-page":"663","article-title":"Algorithms for Inverse Reinforcement Learning","volume-title":"ICML","author":"Ng","year":"2000"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1111\/j.1467-8659.2007.01089.x"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/978-3-642-19457-3_1"},{"volume-title":"Int. Conf. on Cognitive Systems","author":"Muller","article-title":"Socially inspired motion planning for mobile robots in populated environments","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TSSC.1968.300136"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/IROS.2010.5651531"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICRA.2017.7989037"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/IROS.2018.8593871"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref13","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"Ziebart","year":"2008","journal-title":"Aaai"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/IROS.2014.6942731"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1177\/0278364915619772"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.15607\/rss.2012.viii.025"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICRA.2014.6907442"},{"key":"ref18","first-page":"2586","article-title":"Bayesian Inverse Reinforcement Learning","volume-title":"IJCAI","volume":"7","author":"Ramachandran","year":"2007"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICRA.2016.7487452"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1007\/978-3-540-74958-5_25"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/s12369-015-0310-2"},{"key":"ref22","article-title":"Maximum Entropy Deep Inverse Reinforcement Learning","volume":"abs\/1507.04888","author":"Wulfmeier","year":"2016","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/IROS.2018.8593438"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR.2014.283"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/LRA.2020.3048657"},{"key":"ref26","article-title":"Imitation learning from observations by minimizing inverse dynamics disagreement","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Yang","year":"2019"},{"key":"ref27","first-page":"1255","article-title":"Modeling interaction via the principle of maximum causal entropy","volume-title":"ICML","author":"Ziebart","year":"2010"},{"key":"ref28","first-page":"49","article-title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","volume-title":"International Conference on Machine Learning","author":"Finn","year":"2016"},{"key":"ref29","article-title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","volume":"abs\/1611.03852","author":"Finn","year":"2016","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1007\/BF00992699"},{"key":"ref31","article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov","year":"2019"},{"key":"ref32","article-title":"Generative adversarial imitation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Ho","year":"2016"},{"key":"ref33","article-title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","author":"Fu","year":"2017","journal-title":"arXiv"},{"key":"ref34","article-title":"Soft Actor-Critic Algorithms and Applications","author":"Haarnoja","year":"2018","journal-title":"arXiv"},{"key":"ref35","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","volume-title":"ICML","author":"Nair","year":"2010"},{"volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov","article-title":"Decoupled weight decay regularization","key":"ref36"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref38","article-title":"Generative adversarial imitation from observation","volume-title":"International Conference on Machine Learning Workshop on Imitation, Intent, and Interaction (13)","author":"Torabi","year":"2019"},{"key":"ref39","article-title":"Rail: A modular framework for reinforcement-learning-based adversarial imitation learning","author":"Hudson","year":"2021","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1007\/978-3-642-19457-3_1"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1111\/an.1995.36.2.40"},{"key":"ref42","article-title":"Proxemics models for human-aware navigation in robotics: Grounding interaction and personal space models in experimental data from psychology","volume-title":"Proceedings of the 3rd IROS2014 workshop \u201cAssistance and Service Robotics in a Human Environment\u201d","author":"Barnaud","year":"2014"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1016\/j.gaitpost.2007.03.015"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1103\/physreve.51.4282"},{"issue":"2","key":"ref45","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1023\/A:1008986004181","article-title":"Psychological effects of behavior patterns of a mobile personal robot","volume":"10","author":"Butler","year":"2001","journal-title":"Autonomous Robots"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981645.pdf?arnumber=9981645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:36:39Z","timestamp":1706762199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981645","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}