Learning-based model predictive control: Toward safe learning in control

L Hewing, KP Wabersich, M Menner… - Annual Review of …, 2020‏ - annualreviews.org
Recent successes in the field of machine learning, as well as the availability of increased
sensing and computational capabilities in modern control systems, have led to a growing …

Behavioral systems theory in data-driven analysis, signal processing, and control

I Markovsky, F Dörfler - Annual Reviews in Control, 2021‏ - Elsevier
The behavioral approach to systems theory, put forward 40 years ago by Jan C. Willems,
takes a representation-free perspective of a dynamical system as a set of trajectories. Till …

Formulas for data-driven control: Stabilization, optimality, and robustness

C De Persis, P Tesi - IEEE Transactions on Automatic Control, 2019‏ - ieeexplore.ieee.org
In a paper by Willems et al., it was shown that persistently exciting data can be used to
represent the input-output behavior of a linear system. Based on this fundamental result, we …

Data-driven model predictive control with stability and robustness guarantees

J Berberich, J Köhler, MA Müller… - IEEE Transactions on …, 2020‏ - ieeexplore.ieee.org
We propose a robust data-driven model predictive control (MPC) scheme to control linear
time-invariant systems. The scheme uses an implicit model description based on behavioral …

Data informativity: A new perspective on data-driven analysis and control

HJ Van Waarde, J Eising… - … on Automatic Control, 2020‏ - ieeexplore.ieee.org
The use of persistently exciting data has recently been popularized in the context of data-
driven analysis and control. Such data have been used to assess system-theoretic …

Bridging direct and indirect data-driven control formulations via regularizations and relaxations

F Dörfler, J Coulson, I Markovsky - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
In this article, we discuss connections between sequential system identification and control
for linear time-invariant systems, often termed indirect data-driven control, as well as a …

From noisy data to feedback controllers: Nonconservative design via a matrix S-lemma

HJ van Waarde, MK Camlibel… - IEEE Transactions on …, 2020‏ - ieeexplore.ieee.org
In this article, we propose a new method to obtain feedback controllers of an unknown
dynamical system directly from noisy input/state data. The key ingredient of our design is a …

Distributionally robust chance constrained data-enabled predictive control

J Coulson, J Lygeros, F Dörfler - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
In this article we study the problem of finite-time constrained optimal control of unknown
stochastic linear time-invariant (LTI) systems, which is the key ingredient of a predictive …

An overview of systems-theoretic guarantees in data-driven model predictive control

J Berberich, F Allgöwer - Annual Review of Control, Robotics …, 2024‏ - annualreviews.org
The development of control methods based on data has seen a surge of interest in recent
years. When applying data-driven controllers in real-world applications, providing theoretical …

Willems' fundamental lemma for state-space systems and its extension to multiple datasets

HJ Van Waarde, C De Persis… - IEEE Control Systems …, 2020‏ - ieeexplore.ieee.org
Willems et al.'s fundamental lemma asserts that all trajectories of a linear system can be
obtained from a single given one, assuming that a persistency of excitation and a …