Constrained Gaussian Process Learning for Model Predictive Control

被引:9
作者
Matschek, Janine [1 ]
Himmel, Andreas [2 ]
Sundmacher, Kai [2 ,3 ]
Findeisen, Rolf [1 ]
机构
[1] Otto von Guericke Univ, Lab Syst Theory & Automat Control, Magdeburg, Germany
[2] Otto von Guericke Univ, Proc Syst Engn, Magdeburg, Germany
[3] Max Planck Inst Dynam Complex Tech Syst, Magdeburg, Germany
关键词
Gaussian processes; trajectory tracking; learning supported model predictive control; SYSTEMS;
D O I
10.1016/j.ifacol.2020.12.1269
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Many control tasks can be formulated as tracking problems of a known or unknown reference signal. Examples are motion compensation in collaborative robotics, the synchronisation of oscillations for power systems or the reference tracking of recipes in chemical process operation. Both the tracking performance and the stability of the closed-loop system depend strongly on two factors: Firstly, they depend on whether the future reference signal required for tracking is known, and secondly, whether the system can track the reference at all. This paper shows how to use machine learning, i.e. Gaussian processes, to learn a reference from (noisy) data while guaranteeing trackability of the modified desired reference predictions within the framework of model predictive control. Guarantees are provided by adjusting the hyperparameters via a constrained optimisation. Two specific scenarios, i.e. asymptotically constant and periodic references, are discussed. Copyright (C) 2020 The Authors.
引用
收藏
页码:971 / 976
页数:6
相关论文
共 18 条
[1]  
Berkenkamp F, 2015, 2015 EUROPEAN CONTROL CONFERENCE (ECC), P2496, DOI 10.1109/ECC.2015.7330913
[2]  
Blanchini F, 2008, SYST CONTROL-FOUND A, P1
[3]  
Da Veiga S., 2012, Annales de la Faculte des sciences de Toulouse: Mathematiques, V21, P529
[4]  
Faulwasser T, 2011, IEEE DECIS CONTR P, P3381, DOI 10.1109/CDC.2011.6160492
[5]   MPC for tracking of constrained nonlinear systems [J].
Ferramosca, A. ;
Limon, D. ;
Alvarado, I. ;
Alamo, T. ;
Camacho, E. F. .
PROCEEDINGS OF THE 48TH IEEE CONFERENCE ON DECISION AND CONTROL, 2009 HELD JOINTLY WITH THE 2009 28TH CHINESE CONTROL CONFERENCE (CDC/CCC 2009), 2009, :7978-7983
[6]  
Findeisen R., 2020, EUR CONTR C ECC
[7]   Reference and command governors for systems with constraints: A survey on theory and applications [J].
Garone, Emanuele ;
Di Cairano, Stefano ;
Kolmanovsky, Ilya .
AUTOMATICA, 2017, 75 :306-328
[8]   Gaussian Process-Based Predictive Control for Periodic Error Correction [J].
Klenske, Edgar D. ;
Zeilinger, Melanie N. ;
Schoelkopf, Bernhard ;
Hennig, Philipp .
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2016, 24 (01) :110-121
[9]  
Kocijan J, 2004, P AMER CONTR CONF, P2214
[10]  
Kocijan J, 2016, ADV IND CONTROL, P1, DOI 10.1007/978-3-319-21021-6