High-probability stable Gaussian process-supported model predictive control for Lur'e systems

DOI10.1016/j.ejcon.2022.100695zbMath1501.93050OpenAlexW4282977715WikidataQ114184634 ScholiaQ114184634MaRDI QIDQ2095350

Hoang Hai Nguyen, Rolf Findeisen, Maik Pfefferkorn

Publication date: 9 November 2022

Published in: European Journal of Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ejcon.2022.100695

zbMATH Keywords

stabilityGaussian processesmodel predictive controlmachine learningLur'e systemsMPCHilbert space membership

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonlinear systems in control theory (93C10) Model predictive control (93B45)

Uses Software

• SDPT3
• YALMIP

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Solving semidefinite-quadratic-linear programs using SDPT3
• Fault tolerant control using Gaussian processes and model predictive control
• Constrained model predictive control: Stability and optimality
• Nonlinear model predictive control. Theory and algorithms
• Deterministic error bounds for kernel-based learning techniques under bounded noise
• Support Vector Machines
• Existence and design of observers for nonlinear systems: Relation to distance to unobservability
• Linear Matrix Inequalities in System and Control Theory
• SDPT3 — A Matlab software package for semidefinite programming, Version 1.3
• On the terminal region of model predictive control for non-linear systems with input/state constraints
• Convergence of Gaussian Process Regression with Estimated Hyper-Parameters and Applications in Bayesian Inverse Problems
• Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting

This page was built for publication: High-probability stable Gaussian process-supported model predictive control for Lur'e systems