{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:09:03Z","timestamp":1783184943404,"version":"3.54.6"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812122","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T15:36:40Z","timestamp":1657640200000},"page":"462-468","source":"Crossref","is-referenced-by-count":22,"title":["Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC"],"prefix":"10.1109","author":[{"given":"Andrea","family":"Tagliabue","sequence":"first","affiliation":[{"name":"MIT Department of Aeronautics and Astronautics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong-Ki","family":"Kim","sequence":"additional","affiliation":[{"name":"MIT Department of Aeronautics and Astronautics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Everett","sequence":"additional","affiliation":[{"name":"MIT Department of Aeronautics and Astronautics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[{"name":"MIT Department of Aeronautics and Astronautics"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.08.019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2966414"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968287"},{"key":"ref31","article-title":"Query-efficient imitation learning for end-to-end autonomous driving","author":"zhang","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref30","article-title":"An imitation from observation approach to transfer learning with dynamics mismatch","volume":"33","author":"desai","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594090"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561915"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561205"},{"key":"ref34","article-title":"Augmix: A simple data processing method to improve robustness and uncertainty","author":"hendrycks","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989379"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.087"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974653"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.040"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561444"},{"key":"ref16","author":"pomerleau","year":"1989","journal-title":"ALVINN An Autonomous Land Vehicle in a Neural Network"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref18","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref19","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics JMLR Workshop and Conference Proceedings"},{"key":"ref28","author":"laskey","year":"2018","journal-title":"On and off-policy deep imitation learning for robotics"},{"key":"ref4","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"ICINCO (1)"},{"key":"ref27","first-page":"143","article-title":"Dart: Noise injection for robust imitation learning","author":"laskey","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref3","author":"lopez","year":"2019","journal-title":"Robust and Adaptive Model Predictive Control of Nonlinear Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2927955"},{"key":"ref29","article-title":"Grounded action transformation for robot learning in simulation","volume":"31","author":"hanna","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.849"},{"key":"ref8","author":"rawling","year":"0","journal-title":"Industrial large-scale model predictive control with deep neural networks"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814758"},{"key":"ref9","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061759"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3091019"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TRO.2019.2942989","article-title":"Deep drone racing: From simulation to reality with domain randomization","volume":"36","author":"loquercio","year":"2019","journal-title":"IEEE Transactions on Robotics"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"Agile autonomous driving using end-to-end deep imitation learning","author":"pan","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref41","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3001646"},{"key":"ref44","year":"0","journal-title":"snap-stack Autopilot code and host tools for flying snapdragon flight-based vehicles"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref43","author":"ishida","year":"2022","journal-title":"robust-tube-mpc"},{"key":"ref25","first-page":"39","article-title":"Humanoid robots learning to walk faster: From the real world to simulation and back","author":"farchy","year":"0","journal-title":"Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812122.pdf?arnumber=9812122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T19:05:01Z","timestamp":1667502301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812122","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}