{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:40:05Z","timestamp":1765546805270,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/icra48506.2021.9561253","type":"proceedings-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T20:28:35Z","timestamp":1634675315000},"page":"792-798","source":"Crossref","is-referenced-by-count":9,"title":["Model-based Reinforcement Learning with Provable Safety Guarantees via Control Barrier Functions"],"prefix":"10.1109","author":[{"given":"Hongchao","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zhouchi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Clark","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref38","volume":"113","author":"karatzas","year":"2014","journal-title":"Brownian Motion and Stochastic Calculus"},{"article-title":"Temporal logic guided safe reinforcement learning using control barrier functions","year":"2019","author":"li","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.073"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2017.2760863"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1109\/TRO.2017.2659727","article-title":"Safety barrier certificates for collisions-free multirobot systems","volume":"33","author":"wang","year":"2017","journal-title":"IEEE Transactions on Robotics"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3009082"},{"key":"ref36","first-page":"708","article-title":"Learning for safety-critical control with control barrier functions","author":"taylor","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147584"},{"article-title":"Safe exploration in markov decision processes","year":"2012","author":"moldovan","key":"ref10"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"article-title":"Constrained policy optimization","year":"2017","author":"achiam","key":"ref11"},{"key":"ref12","first-page":"6548","article-title":"Safe exploration and optimization of constrained mdps using gaussian processes","author":"wachi","year":"2018","journal-title":"AAAI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509832"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.03.002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7170969"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989015"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/ITSC45102.2020.9294485","article-title":"Training neural network controllers using control barrier functions in the presence of disturbances","author":"yaghoubi","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2465787.2465797"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029455"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36580-X_12"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"article-title":"Adaptive control barrier functions for safety-critical systems","year":"2020","author":"xiao","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.902736"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7172044"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.ifacol.2015.11.154","article-title":"Control barrier certificates for safe swarm behavior","volume":"48","author":"borrmann","year":"2015","journal-title":"IFAC-PapersOnLine"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377796"},{"key":"ref1","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"article-title":"Safe exploration of nonlinear dynamical systems: A predictive safety filter for reinforcement learning","year":"2018","author":"wabersich","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460471"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2920206"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814901"},{"key":"ref42","first-page":"659","article-title":"Uniform error bounds for gaussian process regression with application to safe control","author":"lederer","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"462","DOI":"10.3182\/20070822-3-ZA-2920.00076","article-title":"Constructive safety using control barrier functions","volume":"40","author":"wieland","year":"2007","journal-title":"IFAC Proceedings Volumes"},{"key":"ref41","volume":"2","author":"williams","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.10.005"},{"article-title":"Control barrier functions for stochastic systems","year":"2020","author":"clark","key":"ref25"},{"article-title":"A software package for sequential quadratic programming","year":"1988","author":"kraft","key":"ref43"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","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\/09561253.pdf?arnumber=9561253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T17:33:51Z","timestamp":1673544831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561253","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}