{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:06:14Z","timestamp":1785197174401,"version":"3.55.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8793611","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"8662-8668","source":"Crossref","is-referenced-by-count":121,"title":["Safe Reinforcement Learning With Model Uncertainty Estimates"],"prefix":"10.1109","author":[{"given":"Bjorn","family":"Lutjens","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Everett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref38","article-title":"Bayesian Uncertainty Estimation for Batch Normalized Deep Networks","author":"teye","year":"2018","journal-title":"CoRR"},{"key":"ref33","article-title":"Funnel libraries for real-time robust feedback motion planning","volume":"abs 1601 4037","author":"majumdar","year":"2016","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/S0005-1098(98)00193-9","article-title":"Controllers for reachability specifications for hybrid systems","volume":"35","author":"lygeros","year":"1999","journal-title":"Automatica"},{"key":"ref31","article-title":"Fully Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Safe and Efficient Navigation in Complex Scenarios","author":"fan","year":"2018","journal-title":"CoRR"},{"key":"ref30","author":"amato","year":"2017","journal-title":"Proceedings of Robotics Science and Systems XII"},{"key":"ref37","article-title":"Implicit weight uncertainty in neural networks","volume":"abs 1711 1297","author":"pawlowski","year":"2017","journal-title":"CoRR"},{"key":"ref36","first-page":"5574","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","author":"kendall","year":"0","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.014"},{"key":"ref34","article-title":"Lyapunov design for safe reinforcement learning","author":"perkins","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref40","article-title":"Stein variational policy gradient","volume":"abs 1704 2399","author":"liu","year":"2017","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref12","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00ed","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref13","author":"gal","year":"2016","journal-title":"Uncertainty in deep learning"},{"key":"ref14","author":"geibel","year":"2006","journal-title":"Risk-sensitive approaches for reinforcement learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017940631555"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00600"},{"key":"ref17","author":"tamar","year":"2015","journal-title":"Risk-sensitive and efficient reinforcement learning algorithms"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/11894841_18"},{"key":"ref19","article-title":"Risk-sensitive and robust decision-making: A cvar optimization approach","author":"chow","year":"2015","journal-title":"Advances in Neural Information Processing Systems I (NIPS)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-4541-9"},{"key":"ref4","year":"2016","journal-title":"A Tragic Loss"},{"key":"ref27","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"2017","journal-title":"Proceedings of International Conference on Learning Representations"},{"key":"ref6","year":"2018","journal-title":"Navya student campus mobility"},{"key":"ref29","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","volume":"abs 1702 1182","author":"kahn","year":"2017","journal-title":"CoRR"},{"key":"ref5","article-title":"Predictive positioning and quality of service ridesharing for campus mobility on demand systems","volume":"abs 1609 8116","author":"miller","year":"2016","journal-title":"2017 IEEE Int Conf on Robotics and Automation"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2015.08.005"},{"key":"ref2","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"lakshminarayanan","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref1","article-title":"Concrete problems in AI safety","author":"amodei","year":"2016","journal-title":"CoRR vol abs\/1606 06565"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530971"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0"},{"key":"ref45","article-title":"Gp-ilqg: Data-driven robust optimal control for uncertain nonlinear dynamical systems","volume":"abs 1705 5344","author":"lee","year":"2017","journal-title":"CoRR"},{"key":"ref48","article-title":"Reciprocal n-body collision avoidance","author":"van den berg","year":"2009","journal-title":"ISRR"},{"key":"ref22","first-page":"2348","article-title":"Practical variational inference for neural networks","author":"graves","year":"2011","journal-title":"Advances in Neural Information Processing Systems 24"},{"key":"ref47","article-title":"Openai gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref21","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37 ser ICML’15"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref24","first-page":"4134","article-title":"Bayesian optimization with robust bayesian neural networks","author":"springenberg","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","first-page":"1708","article-title":"Structured and efficient variational deep learning with matrix gaussian posteriors","volume":"48","author":"louizos","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24271-9"},{"key":"ref26","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"0","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref43","article-title":"Social attention: Modeling attention in human crowds","volume":"abs 1710 4689","author":"vemula","year":"2017","journal-title":"CoRR"},{"key":"ref25","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning (ICML-16)"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08793611.pdf?arnumber=8793611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:15:10Z","timestamp":1657854910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793611","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}