{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:21:14Z","timestamp":1783700474491,"version":"3.55.0"},"reference-count":51,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8461249","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"5628-5635","source":"Crossref","is-referenced-by-count":442,"title":["Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation"],"prefix":"10.1109","author":[{"given":"Tianhao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zoe","family":"McCarthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Owen","family":"Jow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dennis","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Imitation from observation: Learning to imitate behaviors from raw video via context translation","author":"liu","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref38","article-title":"Third-person imitation learning","author":"stadie","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref32","first-page":"561","article-title":"Learning movement primitives","author":"schaal","year":"2005","journal-title":"Robotics Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2004.03.002"},{"key":"ref30","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Vision-based multi-task manipulation for inexpensive robots using end-to-end learning from demonstration","author":"rahmatizadeh","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref35","article-title":"Learning from demonstrations for real world reinforcement learning","author":"hester","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2007.4813899"},{"key":"ref28","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","author":"levine","year":"2011","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref27","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref29","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume":"48","author":"finn","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref2","author":"calinon","year":"2009","journal-title":"Robot Programming by Demonstration"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref24","first-page":"6","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume":"1","author":"ross","year":"2011","journal-title":"AISTATS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1089\/109264202760267970"},{"key":"ref26","article-title":"Apprenticeship learning via inverse reinforcement learning","author":"abbeel","year":"2004","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref25","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"1CML"},{"key":"ref50","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"1CML"},{"key":"ref51","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Learning from demonstrations through the use of non-rigid registration","author":"schulman","year":"2013","journal-title":"Proceedings of the 16th International Symposium on Robotics Research (ISRR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5898\/JHRI.2.2.Dragan"},{"key":"ref40","article-title":"Teleoperation of a humanoid robot using full-body motion capture, example movements, and machine learning","author":"stanton","year":"2012","journal-title":"Proc Australasian Conference on Robotics and Automation"},{"key":"ref12","author":"bryson","year":"1975","journal-title":"Applied Optimal Control Optimization Estimation and Control"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718577"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913506757"},{"key":"ref15","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref18","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)"},{"key":"ref19","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"ref5","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936947"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0160-0"},{"key":"ref46","article-title":"Learning dexterous manipulation policies from experience and imitation","author":"kumar","year":"2016","journal-title":"ICRA"},{"key":"ref45","article-title":"Learning grasping interaction with geometry-aware 3d representations","author":"yan","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2737046"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1109\/HUMANOIDS.2015.7363475","article-title":"First-person teleoperation of a humanoid robot","author":"fritsche","year":"2015","journal-title":"IEEE-RAS International Conference on Humanoid Robots (Humanoids)"},{"key":"ref44","article-title":"Communicating robot arm motion intent through mixed reality head-mounted displays","author":"rosen","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363441"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08461249.pdf?arnumber=8461249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:59:45Z","timestamp":1598245185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8461249","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}