{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T16:50:50Z","timestamp":1793724650157,"version":"4.6.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9560893","type":"proceedings-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T20:28:35Z","timestamp":1634675315000},"page":"1140-1146","source":"Crossref","is-referenced-by-count":72,"title":["Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Claudia","family":"Perez-D'Arpino","sequence":"first","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Liu","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Goebel","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Martin-Martin","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018"},{"key":"ref32","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref31","first-page":"482","article-title":"Re-verse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref30","first-page":"1311","article-title":"Automated curriculum learning for neural net-works","author":"graves","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942636"},{"key":"ref35","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref34","article-title":"Tf-agents: A library for reinforcement learning in tensorflow","author":"guadarrama","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140067"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972868"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/11893004_70"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914557874"},{"key":"ref17","article-title":"A survey of machine learning approaches to robotic path-planning","author":"otte","year":"2015","journal-title":"Cs Colorado Edu"},{"key":"ref18","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"739","article-title":"Off-road obstacle avoidance through end-to-end learning","author":"muller","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref4","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197159"},{"key":"ref3","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"coumans","year":"2016"},{"key":"ref6","year":"2020","journal-title":"Project Website and accompanying video"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2964824"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28619-4_25"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref20","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref22","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794062"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref26","first-page":"185","article-title":"Intention-net: Integrating planning and deep learning for goal-directed autonomous navigation","author":"gao","year":"2017","journal-title":"Proceedings of the 1st Annual Conference on Robot Learning vol 78 of Proceedings of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4656"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09560893.pdf?arnumber=9560893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T19:22:14Z","timestamp":1659468134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560893\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560893","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}