Control Theory in the Era of AI: From Closed Loops to Open Challenges

The abundance of available data on the one hand, and the increase in systems complexity prompted by societal challenges on the other, have put research on so-called learning and data-driven methods in the agenda of virtually every engineering field. Control theory is no exception. In fact, some of its traditional fields have close connections with actively researched problems in AI, such as system identification (with supervised regression and classification problems), and stochastic optimal control (with reinforcement learning). Defining features are the presence of dynamics and the active use of feedback, which make imperative to use a theoretical approach for the development of new methodologies. The talk will give an overview of some of our accomplished and ongoing works in the area of data-based modelling and control of dynamical systems. After sharing some of the lessons learned on the way, promising future directions and key challenges in this ever-changing paradigm will be highlighted.

Andrea Iannelli is a tenure-track assistant professor in the Institute for Systems Theory and Automatic Control (IST) at the University of Stuttgart (Germany). Andrea's main research interests are at the intersection of control theory, optimization, and learning, with a particular focus on robust optimization-based control, uncertainty quantification, and sequential decision-making problems.

He obtained the Bachelor and Master degrees in Aerospace Engineering at the University of Pisa (Italy). In April 2019 he completed his PhD at the University of Bristol (UK), funded by the H2020 project FLEXOP, where he focused on the reconciliation between robust control theory and dynamical systems approaches with application to uncertain aerospace systems. From May 2019 to September 2022 he was a PostDoctoral researcher in the Automatic Control Laboratory (IfA) at ETH Zürich (Switzerland). He serves the community as Associated Editor for the International Journal of Robust and Nonlinear Control and as member of the IPC of international conferences such as the Learning for Dynamics & Control conference and the IFAC conference on Nonlinear Model Predictive Control.