{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:17:02Z","timestamp":1768339022961,"version":"3.49.0"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611109","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"12857-12864","source":"Crossref","is-referenced-by-count":2,"title":["ConBaT: Control Barrier Transformer for Safe Robot Learning from Demonstrations"],"prefix":"10.1109","author":[{"given":"Yue","family":"Meng","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Cambridge,MA,USA,02139"}]},{"given":"Sai","family":"Vemprela","sequence":"additional","affiliation":[{"name":"Microsoft Research,Autonomous Systems and Robotics Group,Redmond,WA,USA,98052"}]},{"given":"Rogerio","family":"Bonatti","sequence":"additional","affiliation":[{"name":"Microsoft Research,Autonomous Systems and Robotics Group,Redmond,WA,USA,98052"}]},{"given":"Chuchu","family":"Fan","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Cambridge,MA,USA,02139"}]},{"given":"Ashish","family":"Kapoor","sequence":"additional","affiliation":[{"name":"Microsoft Research,Autonomous Systems and Robotics Group,Redmond,WA,USA,98052"}]}],"member":"263","reference":[{"key":"ref1","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040372"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref5","first-page":"12","article-title":"Robot learning from demonstration","volume-title":"ICML","volume":"97","author":"Atkeson"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794412"},{"key":"ref8","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"30","author":"Berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593758"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.3824"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342381"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.11.154"},{"key":"ref14","article-title":"Semantic navigation with domain knowledge","author":"Braga","year":"2021"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1201\/9781315137667"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3136653"},{"key":"ref19","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2017.2654063"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141657"},{"key":"ref23","first-page":"1724","article-title":"Safe nonlinear control using robust neural lyapunov-barrier functions","volume-title":"Conference on Robot Learning","author":"Dawson"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5772\/5611"},{"key":"ref25","article-title":"Shieldnn: A provably safe nn filter for unsafe nn controllers","author":"Ferlez","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910387173"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412190"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564432"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561561"},{"key":"ref31","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.12716\/1001.07.02.01"},{"key":"ref33","article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27","author":"LeCun","year":"2022"},{"key":"ref34","article-title":"Temporal logic guided safe reinforcement learning using control barrier functions","author":"Li","year":"2019"},{"key":"ref35","first-page":"608","article-title":"Robust regression for safe exploration in control","author":"Liu","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21090-7_25"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636568"},{"key":"ref38","article-title":"Transformers are sample efficient world models","author":"Micheli","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.65"},{"key":"ref40","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng","year":"2000","journal-title":"Icml"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3074695"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560734"},{"key":"ref43","first-page":"77","article-title":"F1tenth: An open-source evaluation environment for continuous control and reinforcement learning","author":"O\u2019Kelly","year":"2020","journal-title":"NeurIPS 2019 Competition and Demonstration Track"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24743-2_32"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142743"},{"key":"ref47","article-title":"Learning safe multi-agent control with decentralized neural barrier certificates","author":"Qin","year":"2021"},{"key":"ref48","article-title":"A generalist agent","author":"Reed","year":"2022"},{"key":"ref49","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Ross"},{"key":"ref50","article-title":"Learning from demonstration","author":"Schaal","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments","volume":"90","author":"Schmidhuber","year":"1990","journal-title":"Institut f\u00fcr Informatik, Technische Universitat M\u00fcnchen. Technical Report FKI-126"},{"key":"ref52","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref53","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref54","article-title":"MuSHR: A low-cost, open-source robotic racecar for education and research","author":"Srinivasa","year":"2019","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341190"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref57","first-page":"12151","article-title":"Safe reinforcement learning via curriculum induction","volume":"33","author":"Turchetta","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561817"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431617"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3182\/20070822-3-ZA-2920.00076"},{"key":"ref63","article-title":"Daydreamer: World models for physical robot learning","author":"Wu","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2656241"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611109.pdf?arnumber=10611109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:14:27Z","timestamp":1723349667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611109","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}