{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:08:18Z","timestamp":1756994898245,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031210891"},{"type":"electronic","value":"9783031210907"}],"license":[{"start":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T00:00:00Z","timestamp":1671062400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T00:00:00Z","timestamp":1671062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-21090-7_25","type":"book-chapter","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T18:11:35Z","timestamp":1671041495000},"page":"419-435","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Sample-Efficient Safe Learning for Online Nonlinear Control with Control Barrier Functions"],"prefix":"10.1007","author":[{"given":"Wenhao","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashish","family":"Kapoor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,15]]},"reference":[{"key":"25_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 22\u201331 (2017)"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Sreenath, K.: Discrete control barrier functions for safety-critical control of discrete systems with application to bipedal robot navigation. In: Robotics: Science and Systems, Cambridge, MA, USA, vol. 13 (2017)","DOI":"10.15607\/RSS.2017.XIII.073"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Ames, A.D., Coogan, S., Egerstedt, M., Notomista, G., Sreenath, K., Tabuada, P.: Control barrier functions: theory and applications. In: 18th European Control Conference (ECC), pp. 3420\u20133431. IEEE (2019)","DOI":"10.23919\/ECC.2019.8796030"},{"issue":"8","key":"25_CR4","doi-asserted-by":"publisher","first-page":"3861","DOI":"10.1109\/TAC.2016.2638961","volume":"62","author":"AD Ames","year":"2017","unstructured":"Ames, A.D., Xu, X., Grizzle, J.W., Tabuada, P.: Control barrier function based quadratic programs for safety critical systems. IEEE Trans. Autom. Control. 62(8), 3861\u20133876 (2017)","journal-title":"IEEE Trans. Autom. Control."},{"key":"25_CR5","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mane, D.: Concrete problems in ai safety (2016). arXiv:1606.06565"},{"key":"25_CR6","unstructured":"Berkenkamp, F., Turchetta, M., Schoellig, A., Krause, A.: Safe model-based reinforcement learning with stability guarantees. In: Advances in Neural Information Processing Systems, pp. 908\u2013918 (2017)"},{"key":"25_CR7","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: Openai gym (2016). arXiv:1606.01540"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, R., Khojasteh, M.J., Ames, A.D., Burdick, J.W.: Safe multi-agent interaction through robust control barrier functions with learned uncertainties. In: 59th IEEE Conference on Decision and Control (CDC), pp. 777\u2013783. IEEE (2020)","DOI":"10.1109\/CDC42340.2020.9304395"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, R., Orosz, G., Murray, R.M., Burdick, J.W.: End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3387\u20133395 (2019)","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Choi, J., Castaneda, F., Tomlin, C., Sreenath, K.: Reinforcement learning for safety-critical control under model uncertainty, using control lyapunov functions and control barrier functions. In: Proceedings of Robotics: Science and Systems. Corvalis, Oregon, USA (2020)","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Clark, A.: Control barrier functions for complete and incomplete information stochastic systems. In: 2019 American Control Conference (ACC), pp. 2928\u20132935. IEEE (2019)","DOI":"10.23919\/ACC.2019.8814901"},{"key":"25_CR12","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: International Conference on Machine Learning, pp. 1329\u20131338 (2016)"},{"issue":"7","key":"25_CR13","doi-asserted-by":"publisher","first-page":"2737","DOI":"10.1109\/TAC.2018.2876389","volume":"64","author":"JF Fisac","year":"2018","unstructured":"Fisac, J.F., Akametalu, A.K., Zeilinger, M.N., Kaynama, S., Gillula, J., Tomlin, C.J.: A general safety framework for learning-based control in uncertain robotic systems. IEEE Trans. Autom. Control 64(7), 2737\u20132752 (2018)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"1","key":"25_CR14","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Gurriet, T., Singletary, A., Reher, J., Ciarletta, L., Feron, E., Ames, A.: Towards a framework for realizable safety critical control through active set invariance. In: 2018 ACM\/IEEE 9th International Conference on Cyber-Physical Systems (ICCPS), pp. 98\u2013106. IEEE (2018)","DOI":"10.1109\/ICCPS.2018.00018"},{"issue":"3\u20134","key":"25_CR16","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1561\/2400000013","volume":"2","author":"E Hazan","year":"2016","unstructured":"Hazan, E.: Introduction to online convex optimization. Found. Trends Optim. 2(3\u20134), 157\u2013325 (2016)","journal-title":"Found. Trends Optim."},{"issue":"7","key":"25_CR17","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1177\/0278364920913938","volume":"39","author":"FR Hogan","year":"2020","unstructured":"Hogan, F.R., Rodriguez, A.: Reactive planar non-prehensile manipulation with hybrid model predictive control. Int. J. Robot. Res. 39(7), 755\u2013773 (2020)","journal-title":"Int. J. Robot. Res."},{"key":"25_CR18","unstructured":"Kakade, S., Krishnamurthy, A., Lowrey, K., Ohnishi, M., Sun, W.: Information theoretic regret bounds for online nonlinear control. Adv. Neural Inf. Process. Syst. 33 (2020)"},{"key":"25_CR19","unstructured":"Khojasteh, M.J., Dhiman, V., Franceschetti, M., Atanasov, N.: Probabilistic safety constraints for learned high relative degree system dynamics. In: Learning for Dynamics and Control, pp. 781\u2013792 (2020)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Koller, T., Berkenkamp, F., Turchetta, M., Krause, A.: Learning-based model predictive control for safe exploration. In: IEEE Conference on Decision and Control (CDC), pp. 6059\u20136066. IEEE (2018)","DOI":"10.1109\/CDC.2018.8619572"},{"key":"25_CR21","first-page":"372","volume":"33","author":"W Luo","year":"2020","unstructured":"Luo, W., Sun, W., Kapoor, A.: Multi-robot collision avoidance under uncertainty with probabilistic safety barrier certificates. Adv. Neural Inf. Process. Syst. 33, 372\u2013383 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"25_CR22","unstructured":"Luo, W., Sun, W., Kapoor, A.: Sample-efficient safe learning for online nonlinear control with control barrier functions (2022). arXiv:2207.14419"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Lyu, Y., Luo, W., Dolan, J.M.: Probabilistic safety-assured adaptive merging control for autonomous vehicles. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 10764\u201310770. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561894"},{"key":"25_CR24","unstructured":"Mania, H., Jordan, M.I., Recht, B.: Active learning for nonlinear system identification with guarantees (2020). arXiv:2006.10277"},{"issue":"6","key":"25_CR25","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1002\/rnc.5132","volume":"31","author":"Z Marvi","year":"2021","unstructured":"Marvi, Z., Kiumarsi, B.: Safe reinforcement learning: a control barrier function optimization approach. Int. J. Robust Nonlinear Control. 31(6), 1923\u20131940 (2021)","journal-title":"Int. J. Robust Nonlinear Control."},{"key":"25_CR26","unstructured":"Moldovan, T.M., Abbeel, P.: Safe exploration in markov decision processes (2012). arXiv:1205.4810"},{"issue":"5","key":"25_CR27","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.1109\/TRO.2019.2920206","volume":"35","author":"M Ohnishi","year":"2019","unstructured":"Ohnishi, M., Wang, L., Notomista, G., Egerstedt, M.: Barrier-certified adaptive reinforcement learning with applications to brushbot navigation. IEEE Trans. Robot. 35(5), 1186\u20131205 (2019)","journal-title":"IEEE Trans. Robot."},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Pickem, D., Glotfelter, P., Wang, L., Mote, M., Ames, A., Feron, E., Egerstedt, M.: The robotarium: a remotely accessible swarm robotics research testbed. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 1699\u20131706. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989200"},{"key":"25_CR29","first-page":"1177","volume":"20","author":"A Rahimi","year":"2007","unstructured":"Rahimi, A., Recht, B.: Random features for large-scale kernel machines. Adv. Neural Inf. Process. Syst. 20, 1177\u20131184 (2007)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"25_CR30","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1146\/annurev-control-053018-023825","volume":"2","author":"B Recht","year":"2019","unstructured":"Recht, B.: A tour of reinforcement learning: the view from continuous control. Annu. Rev. Control. Robot. Auton. Syst. 2, 253\u2013279 (2019)","journal-title":"Annu. Rev. Control. Robot. Auton. Syst."},{"issue":"1","key":"25_CR31","first-page":"2442","volume":"17","author":"D Russo","year":"2016","unstructured":"Russo, D., Van Roy, B.: An information-theoretic analysis of thompson sampling. J. Mach. Learn. Res. 17(1), 2442\u20132471 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Squires, E., Pierpaoli, P., Egerstedt, M.: Constructive barrier certificates with applications to fixed-wing aircraft collision avoidance. In: IEEE Conference on Control Technology and Applications (CCTA), pp. 1656\u20131661. IEEE (2018)","DOI":"10.1109\/CCTA.2018.8511342"},{"key":"25_CR33","unstructured":"Taylor, A., Singletary, A., Yue, Y., Ames, A.: Learning for safety-critical control with control barrier functions. In: Learning for Dynamics and Control, pp. 708\u2013717. PMLR (2020)"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Taylor, A.J., Ames, A.D.: Adaptive safety with control barrier functions. In: 2020 American Control Conference (ACC), pp. 1399\u20131405. IEEE (2020)","DOI":"10.23919\/ACC45564.2020.9147463"},{"key":"25_CR35","first-page":"4312","volume":"29","author":"M Turchetta","year":"2016","unstructured":"Turchetta, M., Berkenkamp, F., Krause, A.: Safe exploration in finite markov decision processes with gaussian processes. Adv. Neural Inf. Process. Syst. 29, 4312\u20134320 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Wagener, N., Cheng, C., Sacks, J., Boots, B.: An online learning approach to model predictive control. In: Proceedings of Robotics: Science and Systems (RSS) (2019)","DOI":"10.15607\/RSS.2019.XV.033"},{"issue":"3","key":"25_CR37","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TRO.2017.2659727","volume":"33","author":"L Wang","year":"2017","unstructured":"Wang, L., Ames, A.D., Egerstedt, M.: Safety barrier certificates for collisions-free multirobot systems. IEEE Trans. Robot. 33(3), 661\u2013674 (2017)","journal-title":"IEEE Trans. Robot."},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Wang, L., Theodorou, E.A., Egerstedt, M.: Safe learning of quadrotor dynamics using barrier certificates. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 2460\u20132465. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460471"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Williams, G., Wagener, N., Goldfain, B., Drews, P., Rehg, J.M., Boots, B., Theodorou, E.A.: Information theoretic MPC for model-based reinforcement learning. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 1714\u20131721. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Zeng, J., Zhang, B., Sreenath, K.: Safety-critical model predictive control with discrete-time control barrier function, pp. 3882\u20133889 (2021)","DOI":"10.23919\/ACC50511.2021.9483029"},{"issue":"2","key":"25_CR41","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1109\/LRA.2019.2893494","volume":"4","author":"H Zhu","year":"2019","unstructured":"Zhu, H., Alonso-Mora, J.: Chance-constrained collision avoidance for mavs in dynamic environments. IEEE Robot. Autom. Lett. 4(2), 776\u2013783 (2019)","journal-title":"IEEE Robot. Autom. Lett."}],"container-title":["Springer Proceedings in Advanced Robotics","Algorithmic Foundations of Robotics XV"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21090-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T18:19:27Z","timestamp":1671041967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21090-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,15]]},"ISBN":["9783031210891","9783031210907"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21090-7_25","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"type":"print","value":"2511-1256"},{"type":"electronic","value":"2511-1264"}],"subject":[],"published":{"date-parts":[[2022,12,15]]},"assertion":[{"value":"15 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WAFR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on the Algorithmic Foundations of Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":", MD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wafr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/wafr2022.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}