{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:37:50Z","timestamp":1730299070642,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/ssrr.2018.8468640","type":"proceedings-article","created":{"date-parts":[[2018,9,20]],"date-time":"2018-09-20T22:33:06Z","timestamp":1537482786000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Learning Navigation Tasks from Demonstration for Semi-Autonomous Remote Operation of Mobile Robots"],"prefix":"10.1109","author":[{"given":"Barzin","family":"Moridian","sequence":"first","affiliation":[]},{"given":"Anurag","family":"Kamal","sequence":"additional","affiliation":[]},{"given":"Nina","family":"Mahmoudian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Learning to navigate in complex environments","year":"2016","author":"mirowski","key":"ref39"},{"journal-title":"Cog-nitive mapping and planning for visual navigation","year":"2017","author":"gupta","key":"ref38"},{"key":"ref33","first-page":"2094","article-title":"Deep reinforcement learning with double Q-Iearning.","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref31"},{"key":"ref30","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML-15)"},{"journal-title":"Target-driven visual navigation in indoor scenes using deep reinforcement learning","year":"2016","author":"zhu","key":"ref37"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref36"},{"journal-title":"Deep recurrent q-learning for partially observable mdps","year":"2015","author":"hausknecht","key":"ref35"},{"journal-title":"Dueling network architectures for deep reinforcement learning","year":"2015","author":"wang","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1991.131684"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1007\/978-3-662-44851-9_35","article-title":"Boosted bellman residual minimization handling expert demonstrations","author":"piot","year":"2014","journal-title":"Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/21.120050"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5648974"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40686-7_15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989263"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20276"},{"key":"ref17","first-page":"2154","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref19","first-page":"6","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning.","author":"ross","year":"2011","journal-title":"AISTATS"},{"key":"ref28","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning (ICML-13)"},{"key":"ref4","first-page":"170","article-title":"Real time control of a robotic manipulator via unreliable internet connection","volume":"1","author":"malinowski","year":"2001","journal-title":"Industrial Electronics Society 2001 IECON'01 the 27th Annual Conference of the IEEE"},{"journal-title":"Learning from demonstrations for real world reinforcement learning","year":"2017","author":"hester","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1115\/1.4006215"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.887306"},{"key":"ref29","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.1996.568763"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1109\/ROMAN.2004.1374738","article-title":"Study on effective camera images for mobile robot teleoperation","author":"shiroma","year":"2004","journal-title":"Robot and Human Interactive Communication 2004 ROMAN 2004 13th IEEE International Workshop on"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1177\/0278364908099461","article-title":"Position tracking for non-linear teleoperators with variable time delay","volume":"28","author":"nufio","year":"2009","journal-title":"The International Journal of Robotics Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/70.258052"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2015.1039909"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOMW.2011.5928905"},{"key":"ref20","article-title":"Sen-sor modality fusion with CNNs for UGV autonomous driving in indoor environments","author":"patel","year":"2017","journal-title":"International Conference on Intelligent Robots and Systems"},{"key":"ref22","volume":"239","author":"pomerleau","year":"2012","journal-title":"Neural Network Perception for Mobile Robot Guidance"},{"key":"ref21","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref42"},{"journal-title":"Reinforcement and imitation learning via interactive no-regret learning","year":"2014","author":"ross","key":"ref24"},{"key":"ref41","first-page":"3380","article-title":"Direct policy iteration with demonstrations.","author":"chemali","year":"2015","journal-title":"IJCAI"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487174"},{"journal-title":"PLATO Policy Learning using Adaptive Trajectory Optimization","year":"2016","author":"kahn","key":"ref25"}],"event":{"name":"2018 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","start":{"date-parts":[[2018,8,6]]},"location":"Philadelphia, PA, USA","end":{"date-parts":[[2018,8,8]]}},"container-title":["2018 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8457068\/8468601\/08468640.pdf?arnumber=8468640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T21:00:58Z","timestamp":1614978058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8468640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ssrr.2018.8468640","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}