All seminars are held at the Department of Automatic Control, in the seminar room M:2112B on the second floor in the M-building, unless stated otherwise.
Control Seminar Series - Andrea Iannelli
Place: Seminar Room KC 3N27 at Dept. of Automatic Control
Contact: venkatraman [dot] renganathan [at] control [dot] lth [dot] se
Save event to your calendar
The department of Automatic Control is happy to announce a seminar given by Dr. Andrea Iannelli. This seminar is part of the control seminar series.
Speaker: Dr. Andrea Iannelli, University of Stuttgart (Germany)
When: April 27th at 15:30-16:30
Where: Seminar Room KC 3N27
Title: Online Learning for Control: Bringing Sequential Decision Making in the Loop
The increase in systems complexity caused by societal challenges and the push to address more demanding tasks makes the synthesis of policies to achieve desired closed-loop system’s performance a sequential decision making problem under uncertainty. This motivates us to rethink the standard paradigm in control design of synthesizing offline the control algorithm (e.g. a matrix of transfer functions as in loop-shaping or a static map between measured state and input as in model predictive control). In this work we will present our on-going work towards framing control of adaptive systems in changing environments as an online learning problem, whereby the decision-maker takes sequential decisions by solving a series of time-varying optimization problems having a-priori only partial knowledge of the cost functions. This viewpoint inherently takes into account the time-varying and uncertain nature of the problem and considers a different performance metric than those commonly used in control, i.e. regret, which measures the accumulated suboptimality with respect to a clairvoyant decision maker. To understand what online learning can offer in the context of systems theory and control, we analyze two classic system theoretic properties, i.e. stability and robustness, through its lens. Our findings show: the relationship between specific rates of regret and some notions of stability; and how the standard robust control approach of planning for the worst-case fare according to regret.
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 optimization-based control, system identification, 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). During his PostDoc he has been developing theoretical advances in data-driven control theory and system identification, with particular emphasis on methodological approaches for data-based predictions and decisions. For more information, check out his webpage.