Marco C. Campi is Professor of Automatic Control at the University of Brescia, Italy. After receiving in 1988
the doctor degree in electronic engineering from the Politecnico di Milano, Italy, he was a Research Fellow
at the Centro di Teoria dei Sistemi of the National Research Council (CNR) in Milano from 1989 to 1992. In
1992, he joined the University of Brescia. He has held visiting and teaching positions at the Australian
National University, Canberra, Australia; the University of Illinois at Urbana-Champaign, USA; the Centre
for Artificial Intelligence and Robotics, Bangalore, India; the University of Melbourne, Australia; the Kyoto
University, Japan. Marco C. Campi is the chair of the Technical Committee IFAC on Modeling, Identification
and Signal Processing (MISP), and was the Chair of the Technical Committee IFAC on Stochastic Systems (SS)
from 2002 to 2008. He has been in various capacities on the Editorial Board of Automatica, Systems and
Control Letters and the European Journal of Control. In 2008, he received the IEEE CSS George S. Axelby
outstanding paper award for the article “The Scenario Approach to Robust Control Design”. Marco C. Campi
has delivered plenary and semi-plenary addresses at major conferences including CDC, SYSID, and MTNS.
He is a Fellow of IEEE, a member of IFAC, and a member of SIDRA. The research interests of Marco C.
Campi include: randomized methods, system identification, stochastic systems, adaptive and data-based
control, robust optimization, and learning theory.
University of Brescia
Distinguished Lecture Program
Talk Title: Scenario-optimization: a methodology for control, identification and classification
Scenario optimization is a general methodology that enables one to make designs based on knowledge sourced from empirical data. When the scenario design is applied to a new case, its performance is guaranteed by the generalization theory that underpins the method. In this talk, the scenario approach will be presented along with its theoretical foundations. The generality of the scenario approach makes it useful across a variety of fields including control, identification and classification and examples will be provided to highlight its versatility.
Talk Title: Distribution-free results in system identification
Classical theories of system identification are grounded on probabilistic assumptions under which various methods are guaranteed to converge, to be asymptotically efficient, etc. In this talk, we shall contend that theoretical guarantees can be obtained under way less assumptions than traditional theories do and shall make a case for the need to spend more research effort in this direction. This suggests a paradigm shift where prior knowledge only impacts on visible characteristics of the model, such as the extension of the identified region or the width of an interval used for prediction, while the model reliability is guaranteed under minimal a priori assumptions.
Talk Title: Data-based controller design: the virtual reference approach
Virtual Reference Feedback Tuning (VRFT) is a method to design controllers based on empirical data. A reference model is assigned by the user and the method automatically designs the best possible controller according to a 2-norm metric within the considered controller class. This is obtained by recasting the original non-convex controller design as a convex design amenable of implementation by means of a set of input-output measurements obtained from the plant. In this talk, I shall present the foundations of VRFT and shall illustrate it through application studies.