{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T11:20:39Z","timestamp":1773141639711,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T00:00:00Z","timestamp":1710115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2219755"],"award-info":[{"award-number":["2219755"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1R01HL157457"],"award-info":[{"award-number":["1R01HL157457"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Ford Motor Company","doi-asserted-by":"publisher","award":["003778"],"award-info":[{"award-number":["003778"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Konica Minolta Imaging Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,11]]},"DOI":"10.1145\/3610977.3635002","type":"proceedings-article","created":{"date-parts":[[2024,3,10]],"date-time":"2024-03-10T00:19:00Z","timestamp":1710029940000},"page":"820-829","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing Safety in Learning from Demonstration Algorithms via Control Barrier Function Shielding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8433-6246","authenticated-orcid":false,"given":"Yue","family":"Yang","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9238-7342","authenticated-orcid":false,"given":"Letian","family":"Chen","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6053-6259","authenticated-orcid":false,"given":"Zulfiqar","family":"Zaidi","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3729-157X","authenticated-orcid":false,"given":"Sanne","family":"van Waveren","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8558-281X","authenticated-orcid":false,"given":"Arjun","family":"Krishna","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5321-6038","authenticated-orcid":false,"given":"Matthew","family":"Gombolay","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,3,11]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"31","author":"Achiam Joshua","year":"2017","unstructured":"Joshua Achiam, David Held, Aviv Tamar, and Pieter Abbeel. 2017. Constrained Policy Optimization. In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 70), Doina Precup and Yee Whye Teh (Eds.). PMLR, 22--31."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"e_1_3_2_2_3_1","volume-title":"Control barrier functions: Theory and applications. In 2019 18th European control conference (ECC)","author":"Ames Aaron D","unstructured":"Aaron D Ames, Samuel Coogan, Magnus Egerstedt, Gennaro Notomista, Koushil Sreenath, and Paulo Tabuada. 2019. Control barrier functions: Theory and applications. In 2019 18th European control conference (ECC). IEEE, 3420--3431."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040372"},{"key":"e_1_3_2_2_5_1","volume-title":"Conservative Safety Critics for Exploration. In International Conference on Learning Representations. https:\/\/openreview.net\/ forum?id=iaO86DUuKi","author":"Bharadhwaj Homanga","year":"2021","unstructured":"Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, and Animesh Garg. 2021. Conservative Safety Critics for Exploration. In International Conference on Learning Representations. https:\/\/openreview.net\/ forum?id=iaO86DUuKi"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-46681-0_51"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25733"},{"key":"e_1_3_2_2_8_1","volume-title":"International Conference on Machine Learning. PMLR, 1165--1177","author":"Brown Daniel","year":"2020","unstructured":"Daniel Brown, Russell Coleman, Ravi Srinivasan, and Scott Niekum. 2020. Safe imitation learning via fast bayesian reward inference from preferences. In International Conference on Machine Learning. PMLR, 1165--1177."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurevcontrol-"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the International Conference on Human-Robot Interaction (HRI). ACM\/IEEE, 93--94","author":"Cakmak M.","unstructured":"M. Cakmak and L. Takayama. 2013. Towards a comprehensive chore list for domestic robots. In Proceedings of the International Conference on Human-Robot Interaction (HRI). ACM\/IEEE, 93--94."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Steven Carr Nils Jansen Sebastian Junges and Ufuk Topcu. 2022. Safe Reinforcement Learning via Shielding under Partial Observability. arXiv:2204.00755 [cs.AI]","DOI":"10.1609\/aaai.v37i12.26723"},{"key":"e_1_3_2_2_12_1","volume-title":"Learning for Dynamics and Control Conference. PMLR, 286--299","author":"Casta\u00f1eda Fernando","year":"2023","unstructured":"Fernando Casta\u00f1eda, Haruki Nishimura, Rowan Thomas McAllister, Koushil Sreenath, and Adrien Gaidon. 2023. In-Distribution Barrier Functions: Self- Supervised Policy Filters that Avoid Out-of-Distribution States. In Learning for Dynamics and Control Conference. PMLR, 286--299."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374791"},{"key":"e_1_3_2_2_14_1","volume-title":"Learning from suboptimal demonstration via self-supervised reward regression. arXiv preprint arXiv:2010.11723","author":"Chen Letian","year":"2020","unstructured":"Letian Chen, Rohan Paleja, and Matthew Gombolay. 2020. Learning from suboptimal demonstration via self-supervised reward regression. arXiv preprint arXiv:2010.11723 (2020)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"e_1_3_2_2_16_1","volume-title":"Reinforcement learning for safety-critical control under model uncertainty, using control lyapunov functions and control barrier functions. arXiv preprint arXiv:2004.07584","author":"Choi Jason","year":"2020","unstructured":"Jason Choi, Fernando Castaneda, Claire J Tomlin, and Koushil Sreenath. 2020. Reinforcement learning for safety-critical control under model uncertainty, using control lyapunov functions and control barrier functions. arXiv preprint arXiv:2004.07584 (2020)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44051-0_14"},{"key":"e_1_3_2_2_18_1","volume-title":"Learning Responsibility Allocations for Safe Human-Robot Interaction with Applications to Autonomous Driving. arXiv preprint arXiv:2303.03504","author":"Cosner Ryan K","year":"2023","unstructured":"Ryan K Cosner, Yuxiao Chen, Karen Leung, and Marco Pavone. 2023. Learning Responsibility Allocations for Safe Human-Robot Interaction with Applications to Autonomous Driving. arXiv preprint arXiv:2303.03504 (2023)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9993193"},{"key":"e_1_3_2_2_20_1","unstructured":"Gal Dalal Krishnamurthy Dvijotham Matej Vecerik Todd Hester Cosmin Paduraru and Yuval Tassa. 2018. Safe Exploration in Continuous Action Spaces. arXiv:1801.08757 [cs.AI]"},{"key":"e_1_3_2_2_21_1","volume-title":"Learning robust rewards with adversarial inverse reinforcement learning. arXiv preprint arXiv:1710.11248","author":"Fu Justin","year":"2017","unstructured":"Justin Fu, Katie Luo, and Sergey Levine. 2017. Learning robust rewards with adversarial inverse reinforcement learning. arXiv preprint arXiv:1710.11248 (2017)."},{"key":"e_1_3_2_2_22_1","volume-title":"4th Robot Learning Workshop: Self-Supervised and Lifelong Learning at NeurIPS","author":"Gallou\u00e9dec Quentin","year":"2021","unstructured":"Quentin Gallou\u00e9dec, Nicolas Cazin, Emmanuel Dellandr\u00e9a, and Liming Chen. 2021. panda-gym: Open-Source Goal-Conditioned Environments for Robotic Learning. 4th Robot Learning Workshop: Self-Supervised and Lifelong Learning at NeurIPS (2021)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444664"},{"key":"e_1_3_2_2_24_1","volume-title":"Analyzing the effects of humanaware motion planning on close-proximity human--robot collaboration. Human factors 57, 1","author":"Lasota Przemyslaw A","year":"2015","unstructured":"Przemyslaw A Lasota and Julie A Shah. 2015. Analyzing the effects of humanaware motion planning on close-proximity human--robot collaboration. Human factors 57, 1 (2015), 21--33."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC55779.2023.10156279"},{"key":"e_1_3_2_2_26_1","volume-title":"Learning hybrid control barrier functions from data. arXiv preprint arXiv:2011.04112","author":"Lindemann Lars","year":"2020","unstructured":"Lars Lindemann, Haimin Hu, Alexander Robey, Hanwen Zhang, Dimos V Dimarogonas, Stephen Tu, and Nikolai Matni. 2020. Learning hybrid control barrier functions from data. arXiv preprint arXiv:2011.04112 (2020)."},{"key":"e_1_3_2_2_27_1","unstructured":"Lars Lindemann Alexander Robey Lejun Jiang Stephen Tu and N. Matni. 2021. Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations. ArXiv abs\/2111.09971 (2021)."},{"key":"e_1_3_2_2_28_1","first-page":"25621","article-title":"Learning barrier certificates: Towards safe reinforcement learning with zero training-time violations","volume":"34","author":"Luo Yuping","year":"2021","unstructured":"Yuping Luo and Tengyu Ma. 2021. Learning barrier certificates: Towards safe reinforcement learning with zero training-time violations. Advances in Neural Information Processing Systems 34 (2021), 25621--25632.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636468"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593865"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA48906.2021.9658862"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the 29th International Conference on Machine Learning, ICML 2012","author":"Moldovan Teodor Mihai","year":"2012","unstructured":"Teodor Mihai Moldovan and Pieter Abbeel. 2012. Safe Exploration in Markov Decision Processes. In Proceedings of the 29th International Conference on Machine Learning, ICML 2012, Edinburgh, Scotland, UK, June 26 - July 1, 2012. icml.cc \/ Omnipress. http:\/\/icml.cc\/2012\/papers\/838.pdf"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"e_1_3_2_2_35_1","volume-title":"Learning safe multi-agent control with decentralized neural barrier certificates. arXiv preprint arXiv:2101.05436","author":"Qin Zengyi","year":"2021","unstructured":"Zengyi Qin, Kaiqing Zhang, Yuxiao Chen, Jingkai Chen, and Chuchu Fan. 2021. Learning safe multi-agent control with decentralized neural barrier certificates. arXiv preprint arXiv:2101.05436 (2021)."},{"key":"e_1_3_2_2_36_1","volume-title":"Recent advances in robot learning from demonstration. Annual review of control, robotics, and autonomous systems 3","author":"Ravichandar Harish","year":"2020","unstructured":"Harish Ravichandar, Athanasios S Polydoros, Sonia Chernova, and Aude Billard. 2020. Recent advances in robot learning from demonstration. Annual review of control, robotics, and autonomous systems 3 (2020), 297--330."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303785"},{"key":"e_1_3_2_2_38_1","volume-title":"Evaluating trust and safety in HRI: Practical issues and ethical challenges. Emerging Policy and Ethics of Human-Robot Interaction","author":"Salem Maha","year":"2015","unstructured":"Maha Salem and Kerstin Dautenhahn. 2015. Evaluating trust and safety in HRI: Practical issues and ethical challenges. Emerging Policy and Ethics of Human-Robot Interaction (2015)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3523760.3523785"},{"key":"e_1_3_2_2_40_1","volume-title":"Maximum likelihood constraint inference for inverse reinforcement learning. arXiv preprint arXiv:1909.05477","author":"Scobee Dexter RR","year":"2019","unstructured":"Dexter RR Scobee and S Shankar Sastry. 2019. Maximum likelihood constraint inference for inverse reinforcement learning. arXiv preprint arXiv:1909.05477 (2019)."},{"key":"e_1_3_2_2_41_1","unstructured":"Krishnan Srinivasan Benjamin Eysenbach Sehoon Ha Jie Tan and Chelsea Finn. 2020. Learning to be Safe: Deep RL with a Safety Critic. arXiv:2010.14603 [cs.LG]"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341190"},{"key":"e_1_3_2_2_43_1","volume-title":"Reward Constrained Policy Optimization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkfrvsA9FX","author":"Tessler Chen","year":"2019","unstructured":"Chen Tessler, Daniel J. Mankowitz, and Shie Mannor. 2019. Reward Constrained Policy Optimization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkfrvsA9FX"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"e_1_3_2_2_45_1","unstructured":"Brijen Thananjeyan Ashwin Balakrishna Ugo Rosolia Felix Li Rowan McAllister Joseph E. Gonzalez Sergey Levine Francesco Borrelli and Ken Goldberg. 2020. Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep"},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings of the 2023 ACM\/IEEE International Conference on Human-Robot Interaction. 446--455","author":"vanWaveren Sanne","year":"2023","unstructured":"Sanne vanWaveren, Rasmus Rudling, Iolanda Leite, Patric Jensfelt, and Christian Pek. 2023. Increasing perceived safety in motion planning for human-drone interaction. In Proceedings of the 2023 ACM\/IEEE International Conference on Human-Robot Interaction. 446--455."},{"key":"e_1_3_2_2_47_1","volume-title":"Deep reinforcement learning for autonomous driving. arXiv preprint arXiv:1811.11329","author":"Wang Sen","year":"2018","unstructured":"Sen Wang, Daoyuan Jia, and Xinshuo Weng. 2018. Deep reinforcement learning for autonomous driving. arXiv preprint arXiv:1811.11329 (2018)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.094"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1993.181"},{"key":"e_1_3_2_2_50_1","volume-title":"Safe Exploration of Reinforcement Learning with Data-Driven Control Barrier Function. In 2022 China Automation Congress (CAC). 1008--1013","author":"Zhang Chenlin","year":"2022","unstructured":"Chenlin Zhang, Shaochen Wang, Shaofeng Meng, and Zhen Kan. 2022. Safe Exploration of Reinforcement Learning with Data-Driven Control Barrier Function. In 2022 China Automation Congress (CAC). 1008--1013. https:\/\/doi.org\/10.1109\/ CAC57257.2022.10055848"},{"key":"e_1_3_2_2_51_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","author":"Zhang Jesse","year":"2020","unstructured":"Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, and Dinesh Jayaraman. 2020. Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 11055--11065. https:\/\/proceedings.mlr.press\/v119\/zhang20e.html"}],"event":{"name":"HRI '24: ACM\/IEEE International Conference on Human-Robot Interaction","location":"Boulder CO USA","acronym":"HRI '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610977.3635002","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610977.3635002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T16:32:09Z","timestamp":1756398729000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610977.3635002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,11]]},"references-count":51,"alternative-id":["10.1145\/3610977.3635002","10.1145\/3610977"],"URL":"https:\/\/doi.org\/10.1145\/3610977.3635002","relation":{},"subject":[],"published":{"date-parts":[[2024,3,11]]},"assertion":[{"value":"2024-03-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}