{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:33:42Z","timestamp":1743064422893,"version":"3.37.3"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073011","92271115"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101400"],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1016\/j.ins.2023.118977","type":"journal-article","created":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T23:26:08Z","timestamp":1682119568000},"page":"118977","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":10,"special_numbering":"C","title":["Composite adaptive online inverse optimal control approach to human behavior learning"],"prefix":"10.1016","volume":"638","author":[{"given":"Jie","family":"Lin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2331-702X","authenticated-orcid":false,"given":"Mi","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4366-5147","authenticated-orcid":false,"given":"Huai-Ning","family":"Wu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.ins.2023.118977_b0005","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s10111-009-0134-7","article-title":"Principles of adjustable autonomy: a framework for resilient human\u2013machine cooperation","volume":"12","author":"Zieba","year":"2010","journal-title":"Cognit. Technol. Work"},{"issue":"6","key":"10.1016\/j.ins.2023.118977_b0010","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1109\/TAC.1974.1100740","article-title":"Identification of human driver models in car following","volume":"19","author":"Burnham","year":"1974","journal-title":"IEEE Trans. Autom. Control."},{"key":"10.1016\/j.ins.2023.118977_b0015","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1080\/00423114.2012.715653","article-title":"Linear quadratic game and non-cooperative predictive methods for potential application to modelling driver-AFS interactive steering control","volume":"51","author":"Na","year":"2013","journal-title":"Vehicle Syst Dyn."},{"issue":"2","key":"10.1016\/j.ins.2023.118977_b0020","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/MELE.2018.2816844","article-title":"IoT-enabled humans in the loop for energy management systems: promoting building occupants\u2019 participation in optimizing energy consumption","volume":"6","author":"Bisadi","year":"2018","journal-title":"IEEE Electrific. Mag."},{"issue":"3","key":"10.1016\/j.ins.2023.118977_b0025","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1109\/THFE.1967.234304","article-title":"A review of quasi-linear pilot models","volume":"8","author":"Mcruer","year":"1967","journal-title":"IEEE Trans. Hum. Factors Electron."},{"key":"10.1016\/j.ins.2023.118977_b0030","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1016\/j.arcontrol.2017.09.009","article-title":"Review of control models for human pilot behavior","volume":"44","author":"Xu","year":"2017","journal-title":"Annu. Rev. Control"},{"key":"10.1016\/j.ins.2023.118977_b0035","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1016\/j.ins.2021.03.043","article-title":"Nonlinear control using human behavior learning","volume":"569","author":"Perrusqu\u00eda","year":"2021","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2023.118977_b0040","doi-asserted-by":"crossref","unstructured":"M. Kuderer, S. Gulati, W. Burgard, Learning driving styles for autonomous vehicles from demonstration, in Proc. IEEE Int. Conf. Robot. Automat. (ICRA), (2015) 2641\u20132646.","DOI":"10.1109\/ICRA.2015.7139555"},{"key":"10.1016\/j.ins.2023.118977_b0045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ins.2020.01.023","article-title":"An end-to-end inverse reinforcement learning by a boosting approach with relative entropy","volume":"520","author":"Zhang","year":"2020","journal-title":"Inf. Sci."},{"issue":"5","key":"10.1016\/j.ins.2023.118977_b0050","doi-asserted-by":"crossref","first-page":"2581","DOI":"10.1109\/TMECH.2015.2510165","article-title":"Learning compliant movement primitives through demonstration and statistical generalization","volume":"21","author":"Denisa","year":"2016","journal-title":"IEEE\/ASME Trans. Mechatr."},{"issue":"2","key":"10.1016\/j.ins.2023.118977_b0055","first-page":"1","article-title":"Learning and personalizing socially assistive robot behaviors to aid with activities of daily living","volume":"7","author":"Moro","year":"2018","journal-title":"ACM Trans. Interact. Intell. Syst."},{"issue":"2","key":"10.1016\/j.ins.2023.118977_b0060","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1109\/TSMCB.2006.886952","article-title":"On learning, representing, and generalizing a task in a humanoid robot","volume":"37","author":"Calinon","year":"2007","journal-title":"IEEE Trans. Syst., Man, Cybern. B, Cybern."},{"key":"10.1016\/j.ins.2023.118977_b0065","doi-asserted-by":"crossref","unstructured":"P. Englert, A. Paraschos, J. Peters, M. P. Deisenroth, Model-based imitation learning by probabilistic trajectory matching, in Proc. IEEE Int. Conf. Robot. Automat. (2013) 1922-1927.","DOI":"10.1109\/ICRA.2013.6630832"},{"issue":"1","key":"10.1016\/j.ins.2023.118977_b0070","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1146\/annurev-control-100819-063206","article-title":"Recent advances in robot learning from demonstration","volume":"3","author":"Ravichandar","year":"2020","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"10.1016\/j.ins.2023.118977_b0075","doi-asserted-by":"crossref","unstructured":"P. Abbeel, A. Y. Ng, Apprenticeship learning via inverse reinforcement learning, in Proc. 21st Int. Conf. Mach. Learn. Banff, AB, Canada (2004) 1-8.","DOI":"10.1145\/1015330.1015430"},{"key":"10.1016\/j.ins.2023.118977_b0080","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.arcontrol.2020.06.001","article-title":"From inverse optimal control to inverse reinforcement learning: a historical review","volume":"50","author":"Ab Azar","year":"2020","journal-title":"Annu. Rev. Control"},{"key":"10.1016\/j.ins.2023.118977_b0085","unstructured":"A. Y. Ng, S. J. Russell, Algorithms for inverse reinforcement learning, in Proc. 17th Int. Conf. Mach. Learn. (2000) 663-670."},{"key":"10.1016\/j.ins.2023.118977_b0090","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.engappai.2016.01.024","article-title":"Adaptive learning of human motor behaviors: An evolving inverse optimal control approach","volume":"50","author":"El-Hussieny","year":"2016","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"2","key":"10.1016\/j.ins.2023.118977_b0095","doi-asserted-by":"crossref","first-page":"349","DOI":"10.2514\/1.G002792","article-title":"Inference of aircraft intent via inverse optimal control including second-order optimality condition","volume":"41","author":"Yokoyama","year":"2018","journal-title":"J. Guid. Control Dyn."},{"key":"10.1016\/j.ins.2023.118977_b0100","doi-asserted-by":"crossref","unstructured":"S. Arora, P. Doshi, A survey of inverse reinforcement learning: Challenges, methods and progress, Artif. Intell., vol. 297, 2021, Art. no. 103500.","DOI":"10.1016\/j.artint.2021.103500"},{"issue":"1","key":"10.1016\/j.ins.2023.118977_b0105","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1115\/1.3653115","article-title":"When is a linear control system optimal?","volume":"86","author":"Kalman","year":"1964","journal-title":"J. Basic Eng."},{"year":"1966","series-title":"The Inverse Problem of Optimal Control","author":"Anderson","key":"10.1016\/j.ins.2023.118977_b0110"},{"issue":"2","key":"10.1016\/j.ins.2023.118977_b0115","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1137\/0322022","article-title":"A complete optimality condition in the inverse problem of optimal control","volume":"22","author":"Fujii","year":"1984","journal-title":"SIAM J. Control Optim."},{"issue":"2","key":"10.1016\/j.ins.2023.118977_b0120","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/TCST.2014.2343935","article-title":"Solutions to the inverse LQR problem with application to biological systems analysis","volume":"23","author":"Priess","year":"2014","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"10.1016\/j.ins.2023.118977_b0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2020.108977","article-title":"Continuous-time inverse quadratic optimal control problem","volume":"117","author":"Li","year":"2020","journal-title":"Automatica"},{"issue":"4","key":"10.1016\/j.ins.2023.118977_b0130","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1007\/s10489-018-1331-y","article-title":"Inverse discounted-based LQR algorithm for learning human movement behaviors","volume":"49","author":"El-Hussieny","year":"2019","journal-title":"Appl. Intell."},{"key":"10.1016\/j.ins.2023.118977_b0135","doi-asserted-by":"crossref","DOI":"10.1109\/TNSRE.2022.3180690","article-title":"Adaptive reference inverse optimal control for natural walking with musculoskeletal models","author":"Weng","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"10.1016\/j.ins.2023.118977_b0140","doi-asserted-by":"crossref","unstructured":"A. Keshavarz, Y. Wang, S. Boyd, Imputing a convex objective function, in Proc. IEEE Int. Symp. Intell. Control (ISIC), Denver, CO, USA, (2011) 613-619.","DOI":"10.1109\/ISIC.2011.6045410"},{"key":"10.1016\/j.ins.2023.118977_b0145","doi-asserted-by":"crossref","unstructured":"A.-S. Puydupin-Jamin, M. Johnson, T. Bretl, A convex approach to inverse optimal control and its application to modeling human locomotion, in Proc. IEEE ICRA, (2012) 531\u2013536.","DOI":"10.1109\/ICRA.2012.6225317"},{"key":"10.1016\/j.ins.2023.118977_b0150","doi-asserted-by":"crossref","unstructured":"M. Johnson, N. Aghasadeghi, T. Bretl, Inverse optimal control for deterministic continuous-time nonlinear systems, in Proc. IEEE 52nd Annu. Conf. Decis. Control (CDC), Florence, Italy, (2013) 2906\u20132913.","DOI":"10.1109\/CDC.2013.6760325"},{"key":"10.1016\/j.ins.2023.118977_b0155","doi-asserted-by":"crossref","unstructured":"E. Pauwels, D. Henrion, J.-B. Lasserre, Inverse optimal control with polynomial optimization, in Proc. 53rd IEEE Conf. Decis. Control, Dec. (2014) 5581-5586.","DOI":"10.1109\/CDC.2014.7040262"},{"issue":"10","key":"10.1016\/j.ins.2023.118977_b0160","doi-asserted-by":"crossref","first-page":"10570","DOI":"10.1109\/TCYB.2021.3062856","article-title":"Inverse reinforcement learning in tracking control based on inverse optimal control","volume":"52","author":"Xue","year":"2022","journal-title":"IEEE Trans. Cybern."},{"issue":"12","key":"10.1016\/j.ins.2023.118977_b0165","doi-asserted-by":"crossref","first-page":"13083","DOI":"10.1109\/TCYB.2021.3100749","article-title":"Robust inverse Q-learning for continuous-time linear systems in adversarial environments","volume":"52","author":"Lian","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.ins.2023.118977_b0170","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2020.109109","article-title":"Online inverse optimal control for control-constrained discrete-time systems on finite and infinite horizons","volume":"120","author":"Molloy","year":"2020","journal-title":"Automatica"},{"issue":"5","key":"10.1016\/j.ins.2023.118977_b0175","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1109\/THMS.2022.3155369","article-title":"Online learning human behavior for a class of human-in-the-loop systems via adaptive inverse optimal control","volume":"52","author":"Wu","year":"2022","journal-title":"IEEE T Hum.-Mach. Syst."},{"year":"1994","series-title":"Linear Matrix Inequalities in System and Control Theory","author":"Boyd","key":"10.1016\/j.ins.2023.118977_b0180"},{"year":"1995","series-title":"LMI Control Toolbox, Natick","author":"Gahinet","key":"10.1016\/j.ins.2023.118977_b0185"},{"issue":"2","key":"10.1016\/j.ins.2023.118977_b0190","doi-asserted-by":"crossref","first-page":"592","DOI":"10.2514\/1.46866","article-title":"Theory and flight-test validation of a concurrent-learning adaptive controller","volume":"34","author":"Chowdhary","year":"2011","journal-title":"J. Guid. Control Dyn."},{"issue":"1","key":"10.1016\/j.ins.2023.118977_b0195","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0005-1098(82)90021-8","article-title":"Exponential convergence of adaptive identification and control algorithms","volume":"18","author":"Anderson","year":"1982","journal-title":"Automatica"},{"issue":"2","key":"10.1016\/j.ins.2023.118977_b0200","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1016\/j.jfranklin.2019.04.001","article-title":"Composite adaptive control for bilateral teleoperation systems without persistency of excitation","volume":"357","author":"Li","year":"2020","journal-title":"J. Franklin Inst."},{"key":"10.1016\/j.ins.2023.118977_b0205","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.neucom.2017.03.053","article-title":"Data-based adaptive neural network optimal output feedback control for nonlinear systems with actuator saturation","volume":"247","author":"Wang","year":"2017","journal-title":"Neurocomputing"},{"year":"2003","series-title":"Adaptive Control Design and Analysis","author":"Tao","key":"10.1016\/j.ins.2023.118977_b0210"},{"year":"1989","series-title":"Optimal Control: Linear Quadratic Methods","author":"Anderson","key":"10.1016\/j.ins.2023.118977_b0215"},{"issue":"11","key":"10.1016\/j.ins.2023.118977_b0220","doi-asserted-by":"crossref","first-page":"2692","DOI":"10.1109\/TAC.2009.2031580","article-title":"Combined\/composite model reference adaptive control","volume":"54","author":"Lavretsky","year":"2009","journal-title":"IEEE Trans. Autom. Control"},{"issue":"3","key":"10.1016\/j.ins.2023.118977_b0225","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1109\/TAC.2017.2737324","article-title":"Composite model reference adaptive control with parameter convergence under finite excitation","volume":"63","author":"Cho","year":"2018","journal-title":"IEEE Trans. Autom. Control"},{"year":"2002","series-title":"Nonlinear Systems","author":"Khalil","key":"10.1016\/j.ins.2023.118977_b0230"},{"year":"2005","series-title":"Vehicle Dynamics and Control","author":"Rajamani","key":"10.1016\/j.ins.2023.118977_b0235"},{"year":"2009","series-title":"Introduction to Algorithms","author":"Cormen","key":"10.1016\/j.ins.2023.118977_b0240"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025523005467?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025523005467?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T00:32:38Z","timestamp":1729297958000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025523005467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":48,"alternative-id":["S0020025523005467"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2023.118977","relation":{},"ISSN":["0020-0255"],"issn-type":[{"type":"print","value":"0020-0255"}],"subject":[],"published":{"date-parts":[[2023,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Composite adaptive online inverse optimal control approach to human behavior learning","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2023.118977","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"118977"}}