{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T09:43:25Z","timestamp":1772963005922,"version":"3.50.1"},"reference-count":33,"publisher":"Walter de Gruyter GmbH","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Controller tuning is crucial for closed-loop performance but often involves manual adjustments. Although Bayesian optimization (BO) has been established as a data-efficient method for automated tuning, applying it to large and high-dimensional search spaces remains challenging. We extend a recently proposed local variant of BO to include crash constraints, where the controller can only be successfully evaluated in an <jats:italic>a-priori<\/jats:italic> unknown feasible region. We demonstrate the efficiency of the proposed method through simulations and hardware experiments. Our findings showcase the potential of local BO to enhance controller performance and reduce the time and resources necessary for tuning.<\/jats:p>","DOI":"10.1515\/auto-2023-0181","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T20:23:35Z","timestamp":1712607815000},"page":"281-292","source":"Crossref","is-referenced-by-count":6,"title":["Local Bayesian optimization for controller tuning with crash constraints"],"prefix":"10.1515","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0005-0310","authenticated-orcid":false,"given":"Alexander","family":"von Rohr","sequence":"first","affiliation":[{"name":"9165 Institute for Data Science in Mechanical Engineering, RWTH Aachen University , Aachen , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3747-4499","authenticated-orcid":false,"given":"David","family":"Stenger","sequence":"additional","affiliation":[{"name":"9165 Institute of Automatic Control, RWTH Aachen University , Aachen , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1044-5631","authenticated-orcid":false,"given":"Dominik","family":"Scheurenberg","sequence":"additional","affiliation":[{"name":"9165 Institute of Automatic Control, RWTH Aachen University , Aachen , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2785-2487","authenticated-orcid":false,"given":"Sebastian","family":"Trimpe","sequence":"additional","affiliation":[{"name":"9165 Institute for Data Science in Mechanical Engineering, RWTH Aachen University , Aachen , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","published-online":{"date-parts":[[2024,4,8]]},"reference":[{"key":"2024040820233086124_j_auto-2023-0181_ref_001","doi-asserted-by":"crossref","unstructured":"M. Jelali, \u201cAn overview of control performance assessment technology and industrial applications,\u201d Control Eng. Pract., vol.\u00a014, no.\u00a05, pp.\u00a0441\u2013466, 2006. https:\/\/doi.org\/10.1016\/j.conengprac.2005.11.005.","DOI":"10.1016\/j.conengprac.2005.11.005"},{"key":"2024040820233086124_j_auto-2023-0181_ref_002","doi-asserted-by":"crossref","unstructured":"K. Chatzilygeroudis, V. Vassiliades, F. Stulp, S. Calinon, and J.-B. Mouret, \u201cA survey on policy search algorithms for learning robot controllers in a handful of trials,\u201d IEEE Trans. Robot., vol.\u00a036, no.\u00a02, pp.\u00a0328\u2013347, 2020. https:\/\/doi.org\/10.1109\/tro.2019.2958211.","DOI":"10.1109\/TRO.2019.2958211"},{"key":"2024040820233086124_j_auto-2023-0181_ref_003","doi-asserted-by":"crossref","unstructured":"J. A. Paulson, F. Sorourifar, and A. Mesbah, \u201cA tutorial on derivative-free policy learning methods for interpretable controller representations,\u201d in 2023 American Control Conference (ACC), 2023, pp.\u00a01295\u20131306.","DOI":"10.23919\/ACC55779.2023.10156412"},{"key":"2024040820233086124_j_auto-2023-0181_ref_011","unstructured":"D. Stenger and D. Abel, \u201cBenchmark of bayesian optimization and metaheuristics for control engineering tuning problems with crash constraints,\u201d 2022, arXiv preprint arXiv:2211.02571."},{"key":"2024040820233086124_j_auto-2023-0181_ref_004","doi-asserted-by":"crossref","unstructured":"F. Bachoc, C. Helbert, and V. Picheny, \u201cGaussian process optimization with failures: classification and convergence proof,\u201d J. Global Optim., vol.\u00a078, no.\u00a03, pp.\u00a0483\u2013506, 2020. https:\/\/doi.org\/10.1007\/s10898-020-00920-0.","DOI":"10.1007\/s10898-020-00920-0"},{"key":"2024040820233086124_j_auto-2023-0181_ref_005","doi-asserted-by":"crossref","unstructured":"A. Marco, P. Hennig, J. Bohg, S. Schaal, and S. Trimpe, \u201cAutomatic LQR tuning based on Gaussian process global optimization,\u201d in 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016, pp.\u00a0270\u2013277.","DOI":"10.1109\/ICRA.2016.7487144"},{"key":"2024040820233086124_j_auto-2023-0181_ref_006","doi-asserted-by":"crossref","unstructured":"R. Calandra, A. Seyfarth, J. Peters, and M. P. Deisenroth, \u201cBayesian optimization for learning gaits under uncertainty,\u201d Ann. Math. Artif. Intell., vol.\u00a076, nos. 1\u20132, pp.\u00a05\u201323, 2016. https:\/\/doi.org\/10.1007\/s10472-015-9463-9.","DOI":"10.1007\/s10472-015-9463-9"},{"key":"2024040820233086124_j_auto-2023-0181_ref_007","doi-asserted-by":"crossref","unstructured":"A. Marco, D. Baumann, M. Khadiv, P. Hennig, L. Righetti, and S. Trimpe, \u201cRobot learning with crash constraints,\u201d IEEE Robot. Autom. Lett., vol.\u00a06, no.\u00a02, pp.\u00a01439\u20131446, 2021. https:\/\/doi.org\/10.1109\/lra.2021.3057055.","DOI":"10.1109\/LRA.2021.3057055"},{"key":"2024040820233086124_j_auto-2023-0181_ref_008","unstructured":"S. M\u00fcller, A. von Rohr, and S. Trimpe, \u201cLocal policy search with Bayesian optimization,\u201d Adv. Neural Inf. Process. Syst., vol.\u00a034, pp.\u00a020708\u201320720, 2021."},{"key":"2024040820233086124_j_auto-2023-0181_ref_009","unstructured":"Q. Nguyen, K. Wu, J. Gardner, and R. Garnett, \u201cLocal Bayesian optimization via maximizing probability of descent,\u201d Adv. Neural Inf. Process. Syst., vol.\u00a035, pp.\u00a013190\u201313202, 2022."},{"key":"2024040820233086124_j_auto-2023-0181_ref_010","unstructured":"K. Wu, K. Kim, R. Garnett, and J. R. Gardner, \u201cThe behavior and convergence of local bayesian optimization,\u201d in Thirty-seventh Conference on Neural Information Processing Systems, 2023."},{"key":"2024040820233086124_j_auto-2023-0181_ref_012","unstructured":"N. Srinivas, A. Krause, S. Kakade, and M. Seeger, \u201cGaussian process optimization in the bandit setting: No regret and experimental design,\u201d in International Conference on Machine Learning, 2010, pp.\u00a01015\u20131022."},{"key":"2024040820233086124_j_auto-2023-0181_ref_013","doi-asserted-by":"crossref","unstructured":"O. Andersson, M. Wzorek, P. Rudol, and P. Doherty, \u201cModel-predictive control with stochastic collision avoidance using Bayesian policy optimization,\u201d in 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016, pp.\u00a04597\u20134604.","DOI":"10.1109\/ICRA.2016.7487661"},{"key":"2024040820233086124_j_auto-2023-0181_ref_014","doi-asserted-by":"crossref","unstructured":"H. Chen, S. Bowels, B. Zhang, and T. Fuhlbrigge, \u201cController parameter optimization for complex industrial system with uncertainties,\u201d Meas. Control., vol.\u00a052, nos. 7\u20138, pp.\u00a0888\u2013895, 2019. https:\/\/doi.org\/10.1177\/0020294019830108.","DOI":"10.1177\/0020294019830108"},{"key":"2024040820233086124_j_auto-2023-0181_ref_015","doi-asserted-by":"crossref","unstructured":"Z. Chen, C. Heckman, S. Julier, and N. Ahmed, \u201cWeak in the NEES? Auto-tuning kalman filters with bayesian optimization,\u201d in 2018 21st International Conference on Information Fusion (FUSION), 2018, pp.\u00a01072\u20131079.","DOI":"10.23919\/ICIF.2018.8454982"},{"key":"2024040820233086124_j_auto-2023-0181_ref_016","doi-asserted-by":"crossref","unstructured":"J. Marzat, H. Piet-Lahanier, and E. Walter, \u201cMin-max hyperparameter tuning, with application to fault detection,\u201d IFAC Proc. Vol., vol.\u00a044, no.\u00a01, pp.\u00a012904\u201312909, 2011. https:\/\/doi.org\/10.3182\/20110828-6-it-1002.00476.","DOI":"10.3182\/20110828-6-IT-1002.00476"},{"key":"2024040820233086124_j_auto-2023-0181_ref_017","doi-asserted-by":"crossref","unstructured":"M. Khosravi, V. Behrunani, R. S. Smith, A. Rupenyan, and J. Lygeros, \u201cCascade control: data-driven tuning approach based on Bayesian optimization,\u201d IFAC-PapersOnLine, vol.\u00a053, no.\u00a02, pp.\u00a0382\u2013387, 2020. https:\/\/doi.org\/10.1016\/j.ifacol.2020.12.193.","DOI":"10.1016\/j.ifacol.2020.12.193"},{"key":"2024040820233086124_j_auto-2023-0181_ref_018","doi-asserted-by":"crossref","unstructured":"D. Stenger, M. Nitsch, and D. Abel, \u201cJoint constrained Bayesian optimization of planning, guidance, control, and state estimation of an autonomous underwater vehicle,\u201d in 2022 European Control Conference (ECC), 2022, pp.\u00a01982\u20131987.","DOI":"10.23919\/ECC55457.2022.9838053"},{"key":"2024040820233086124_j_auto-2023-0181_ref_019","doi-asserted-by":"crossref","unstructured":"M. Fiducioso, S. Curi, B. Schumacher, M. Gwerder, and A. Krause, \u201cSafe contextual Bayesian optimization for sustainable room temperature PID control tuning,\u201d in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, (IJCAI-19), 2019, pp.\u00a05850\u20135856.","DOI":"10.24963\/ijcai.2019\/811"},{"key":"2024040820233086124_j_auto-2023-0181_ref_020","doi-asserted-by":"crossref","unstructured":"M. Khosravi, C. K\u00f6nig, M. Maier, R. S. Smith, J. Lygeros, and A. Rupenyan, \u201cSafety-aware cascade controller tuning using constrained Bayesian optimization,\u201d IEEE Trans. Ind. Electron., vol.\u00a070, no.\u00a02, pp.\u00a02128\u20132138, 2023. https:\/\/doi.org\/10.1109\/tie.2022.3158007.","DOI":"10.1109\/TIE.2022.3158007"},{"key":"2024040820233086124_j_auto-2023-0181_ref_021","doi-asserted-by":"crossref","unstructured":"F. Berkenkamp, A. Krause, and A. P. Schoellig, \u201cBayesian optimization with safety constraints: safe and automatic parameter tuning in robotics,\u201d Mach. Learn., vol. 112, no. 10, pp. 3713\u20133747, 2021.","DOI":"10.1007\/s10994-021-06019-1"},{"key":"2024040820233086124_j_auto-2023-0181_ref_022","doi-asserted-by":"crossref","unstructured":"D. Stenger, R. Ritschel, F. Krabbes, R. Vo\u00dfwinkel, and H. Richter, \u201cWhat is the best way to optimally parameterize the MPC cost function for vehicle guidance?\u201d Mathematics, vol.\u00a011, no.\u00a02, p.\u00a0465, 2023. https:\/\/doi.org\/10.3390\/math11020465.","DOI":"10.3390\/math11020465"},{"key":"2024040820233086124_j_auto-2023-0181_ref_023","doi-asserted-by":"crossref","unstructured":"G. Makrygiorgos, A. D. Bonzanini, V. Miller, and A. Mesbah, \u201cPerformance-oriented model learning for control via multi-objective Bayesian optimization,\u201d Comput. Chem. Eng., vol.\u00a0162, p.\u00a0107770, 2022. https:\/\/doi.org\/10.1016\/j.compchemeng.2022.107770.","DOI":"10.1016\/j.compchemeng.2022.107770"},{"key":"2024040820233086124_j_auto-2023-0181_ref_024","unstructured":"L. Fr\u00f6hlich, E. Klenske, J. Vinogradska, C. Daniel, and M. Zeilinger, \u201cNoisy-input entropy search for efficient robust Bayesian optimization,\u201d in Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, Volume 108 of Proceedings of Machine Learning Research, S. Chiappa and R. Calandra, Eds., 2020, pp.\u00a02262\u20132272."},{"key":"2024040820233086124_j_auto-2023-0181_ref_025","doi-asserted-by":"crossref","unstructured":"J. A. Paulson, G. Makrygiorgos, and A. Mesbah, \u201cAdversarially robust Bayesian optimization for efficient auto-tuning of generic control structures under uncertainty,\u201d AIChE J., vol.\u00a068, no.\u00a06, 2022, Art. no. e17591. https:\/\/doi.org\/10.1002\/aic.17591.","DOI":"10.1002\/aic.17591"},{"key":"2024040820233086124_j_auto-2023-0181_ref_026","doi-asserted-by":"crossref","unstructured":"M. Zhu, D. Piga, and A. Bemporad, \u201cC-GLISp: preference-based global optimization under unknown constraints with applications to controller calibration,\u201d IEEE Trans. Control Syst. Technol., vol. 30, no. 5, pp. 1\u201312, 2021.","DOI":"10.1109\/TCST.2021.3136711"},{"key":"2024040820233086124_j_auto-2023-0181_ref_027","doi-asserted-by":"crossref","unstructured":"P. Brunzema, A. Von Rohr, and S. Trimpe, \u201cOn controller tuning with time-varying Bayesian optimization,\u201d in 2022 IEEE 61st Conference on Decision and Control (CDC), 2022, pp.\u00a04046\u20134052.","DOI":"10.1109\/CDC51059.2022.9992649"},{"key":"2024040820233086124_j_auto-2023-0181_ref_028","doi-asserted-by":"crossref","unstructured":"D. Stenger, M. Ay, and D. Abel, \u201cRobust parametrization of a model predictive controller for a CNC machining center using Bayesian optimization,\u201d IFAC-PapersOnLine, vol.\u00a053, no.\u00a02, pp.\u00a010388\u201310394, 2020. https:\/\/doi.org\/10.1016\/j.ifacol.2020.12.2778.","DOI":"10.1016\/j.ifacol.2020.12.2778"},{"key":"2024040820233086124_j_auto-2023-0181_ref_029","doi-asserted-by":"crossref","unstructured":"R. Garnett, Bayesian Optimization, Cambridge, Cambridge University Press, 2023.","DOI":"10.1017\/9781108348973"},{"key":"2024040820233086124_j_auto-2023-0181_ref_030","doi-asserted-by":"crossref","unstructured":"C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning, Cambridge, MIT Press, 2006.","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"2024040820233086124_j_auto-2023-0181_ref_031","doi-asserted-by":"crossref","unstructured":"D. Scheurenberg, S. Stemmler, and D. Abel, \u201cEvaluation of data enhanced model predictive control for a coupled tank system,\u201d in 2023 IEEE Conference on Control Technology and Applications (CCTA), 2023, pp.\u00a079\u201384.","DOI":"10.1109\/CCTA54093.2023.10253100"},{"key":"2024040820233086124_j_auto-2023-0181_ref_032","doi-asserted-by":"crossref","unstructured":"D. Baumann, A. Marco, M. Turchetta, and S. Trimpe, \u201cGoSafe: globally optimal safe robot learning,\u201d in 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021, pp.\u00a04452\u20134458.","DOI":"10.1109\/ICRA48506.2021.9560738"},{"key":"2024040820233086124_j_auto-2023-0181_ref_033","doi-asserted-by":"crossref","unstructured":"B. Sch\u00fcrmann, M. Klischat, N. Kochdumper, and M. Althoff, \u201cFormal safety net control using backward reachability analysis,\u201d IEEE Trans. Autom. Control, vol.\u00a067, no.\u00a011, pp.\u00a05698\u20135713, 2022. https:\/\/doi.org\/10.1109\/tac.2021.3124188.","DOI":"10.1109\/TAC.2021.3124188"}],"container-title":["at - Automatisierungstechnik"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2023-0181\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2023-0181\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T20:24:48Z","timestamp":1712607888000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2023-0181\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,1]]},"references-count":33,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4,8]]},"published-print":{"date-parts":[[2024,4,25]]}},"alternative-id":["10.1515\/auto-2023-0181"],"URL":"https:\/\/doi.org\/10.1515\/auto-2023-0181","relation":{},"ISSN":["0178-2312","2196-677X"],"issn-type":[{"value":"0178-2312","type":"print"},{"value":"2196-677X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,1]]}}}