Speaker| Prof. Florian Dörfler (Swiss Federal Inst. of Tech., Switzerland)
Date|Time October 25, 2024 (Fri) | 14:30~15:35
Place |Room 204, Building 133
Abstract
In the first part of the talk, I share some general perspectives on both classical and contemporary approaches to data-driven control. I will then zoom in on a vibrant stream of work based on behavioral systems theory. I will highlight some success stories (particularly DeePC) and open challenges, especially when it comes to real-time adaptation. Since the adaptation challenge is only poorly understood, the second part of the talk then zooms into a specialized and academic problem setup: namely, the linear quadratic regulator (LQR) which is a cornerstone of automatic control, and that has been widely studied in the data-driven setting. We show how to bridge different problem formulations and propose a novel, direct, and regularized version of LQR. In the third part of the talk, we propose an adaptive method to learn the proposed data-driven LQR. By adaptive, we mean an online method using closed-loop data, in a non episodic fashion, and with recursive algorithmic implementation. Our approach is based on a covariance parameterization of the direct, data-driven, and regularized LQR and an explicit calculation of the policy gradient using a batch of persistently exciting data. Finally, all our theoretical results are validated with simulations and demonstrate the computational and sample efficiency of our method.
Biography
Florian Dörfler is a Professor at the Automatic Control Laboratory at ETH Zürich. He received his Ph.D. degree in Mechanical Engineering from the University of California at Santa Barbara in 2013, and a Diplom degree in Engineering Cybernetics from the University of Stuttgart in 2008. From 2013 to 2014 he was an Assistant Professor at the University of California Los Angeles. He has been serving as the Associate Head of the ETH Zürich Department of Information Technology and Electrical Engineering from 2021 until 2022. His research interests are centered around automatic control, system theory, and optimization. His particular foci are on network systems, data-driven settings, and applications to power systems. He is a recipient of the distinguished young research awards by IFAC (Manfred Thoma Medal 2020) and EUCA (European Control Award 2020). His students were winners or finalists for Best Student Paper awards at the European Control Conference (2013, 2019), the American Control Conference (2016,2024), the Conference on Decision and Control (2020), the PES General Meeting (2020), the PES PowerTech Conference (2017), the International Conference on Intelligent Transportation Systems (2021), the IEEE CSS Swiss Chapter Young Author Best Journal Paper Award (2022,2024), and the IFAC Conference on Nonlinear Model Predictive Control (2024). He is furthermore a recipient of the 2010 ACC Student Best Paper Award, the 2011 O. Hugo Schuck Best Paper Award, the 2012-2014 Automatica Best Paper Award, the 2016 IEEE Circuits and Systems Guillemin-Cauer Best Paper Award, the 2022 IEEE Transactions on Power Electronics Prize Paper Award, the 2024 Control Systems Magazine Outstanding Paper Award, and the 2015 UCSB ME Best PhD award. He is currently serving on the council of the European Control Association and as a senior editor of Automatica.