Prof. Sandra Hirche (Technical University of Munich) gave a talk on November 11th, 2022 in our group about Online Learning Control with Robust Performance guarantees
Biography (简介)
Prof. Sandra Hirche holds the TUM Liesel Beckmann Distinguished Professorship and heads the Chair of Information-oriented Control in the Faculty of Electrical and Computer Engineering at Technical University of Munich (TUM), Germany (since 2013). She received the diploma engineer degree in Aeronautical and Aerospace Engineering in 2002 from the Technical University Berlin, Germany, and the Doctor of Engineering degree in Electrical and Computer Engineering in 2005 from the Technische Universität München, Munich, Germany. From 2005-2007 she has been a PostDoc Fellow of the Japanese Society for the Promotion of Science at the Fujita Laboratory at Tokyo Institute of Technology, Japan. Prior to her present appointment she has been an Associate Professor at TUM. Her main research interests include learning, cooperative, and networked control with applications in human-robot interaction, multi-robot systems, and general robotics. She has published more than 200 papers in international journals, books and refereed conferences. She has received multiple awards such as the Rohde & Schwarz Award for her PhD thesis, the IFAC World Congress Best Poster Award in 2005 and – together with students – Best Paper Awards of IEEE Worldhaptics and IFAC Conference of Manoeuvring and Control of Marine Craft in 2009 and the Outstanding Student Paper Award of the IEEE Conference on Decision and Control 2018. In 2013 she has been awarded with an ERC Starting Grant on the “Control based on Human Models” and in 2019 with the ERC Consolidator Grant on “Safe data-driven control for human-centric systems”. Prof. Sandra Hirche is Fellow of the IEEE and received the IEEE Control System Society Distinguished Member Award. She has served as IEEE Control System Society (CSS) Vice- President for Member Activities (2014/15), as Chair for Student Activities in the IEEE CSS (2009-2014), as Chair of the CSS Awards Subcommittee on “CDC Best Student-Paper Award” (2010-2014), and has been elected member of the Board of Governors of IEEE CSS (2010-2013). She has been Co-Chair of the IFAC TC 1.5 “Networked Control Systems” (2010-2017) and the Co-IPC for the 2020 IFAC World Congress.
Abstract
The control design allowing complex Prof. Sandra Hirche systems to operate in unstructured only partially known and potentially changing environments is one of the great challenges in systems and control. Application domains include robotics in healthcare, autonomous surveillance and rescue, service, and logistics. Apart from adaptability, robust performance guarantees including safety represent critical concerns. In this talk we will present recent results on learning-based control with performance and safety guarantees for highly uncertain systems. In order to achieve high sample efficiency as well as transparency of the system, we will consider a data-augmented model-based approach combining known dynamic models with Gaussian Processes. Epistemic uncertainty due to limited training data will explicitly taken into account in the control design in order to achieve robust behavior of the closed loop system. Online learning as well as realtime capabilities in the presence of resource constraints are further important aspects for which novel approaches will be presented.