IEEE WIE Distinguished Lecturers Program (Virtual)

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 Post Doc 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 Maneuvering 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”. 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).

Talk Topic:

1. Online Learning Control for Personalized Robotic Rehabilitation and Assistance 2. High Performance control for Robots in Extreme Environments 3. “To Sample or not to Sample?” – Efficient Online Learning in Closed Loop Control Systems with Guarantees

Abstract: 

One of the central societal challenges is to prolong independent living for elderly and promote well. Personalized robotic rehabilitation and assistance is considered one of the enabling technologies with control design playing a significant role. Focusing on sensorimotor rehabilitation and assistance, personalized control should be able to adapt to the high inter-personal variability in human motor behavior but also to intra-personal changes over time. Control adaptation is further challenged by the sparsity of person-specific data because calibration routines need to be brief for user acceptance. Above all, guaranteed safety is one of the key requirements. In this talk we will present recent results on learning-based control with performance and safety guarantees for highly uncertain systems with particular focus on challenges arising from personalized rehabilitation and assistance. In order to achieve high sample efficiency as well as transparency of the system, available knowledge of dynamic models will be exploited and and augmented by Bayesian non-parametric model components. Epistemic uncertainty due to limited training data will explicitly be taken into account in the control design in order to achieve uncertainty-aware behavior of the closed loop system. Online learning as well as realtime capabilities are further important aspects discussed in this talk. The results will be demonstrated in user intention-driven shared control designs for upper limb rehabilitation and assistance with exoskeletons.
2. One of the central societal challenges is to prolong independent living for elderly and promote well. Personalized robotic rehabilitation and assistance is considered one of the enabling technologies with control design playing a significant role. Focusing on sensorimotor rehabilitation and assistance, personalized control should be able to adapt to the high inter-personal variability in human motor behavior but also to intra-personal changes over time. Control adaptation is further challenged by the sparsity of person-specific data because calibration routines need to be brief for user acceptance. Above all, guaranteed safety is one of the key requirements. In this talk we will present recent results on learning-based control with performance and safety guarantees for highly uncertain systems with particular focus on challenges arising from personalized rehabilitation and assistance. In order to achieve high sample efficiency as well as transparency of the system, available knowledge of dynamic models will be exploited and and augmented by Bayesian non-parametric model components. Epistemic uncertainty due to limited training data will explicitly be taken into account in the control design in order to achieve uncertainty-aware behavior of the closed loop system. Online learning as well as real time capabilities are further important aspects discussed in this talk. The results will be demonstrated in user intention-driven shared control designs for upper limb rehabilitation and assistance with exoskeletons.
3. Online learning in closed loop control systems is very attractive because it allows the automated identification of highly nonlinear dynamical systems as well as a fast adaptation to dynamically changing environments. Yet, depending on the application the data collection and the training of models is costly if not even prohibitive. On the one hand, the training is computationally expensive and might compromise real-time performance. In particular in non-parametric learning approaches as e.g. in Gaussian Processes, the computational tractability is tied to the number of training data. As such it is important to understand how informative training samples are and further how to improve algorithmic efficiency of training and prediction. In this talk we will demonstrate that the control task in addition to the underlying system dynamics has a strong influence on the required sample complexity. Employing Bayesian principles, we explore methods to quantify epistemic uncertainty with respect to control objectives and how they can be exploited to achieve a high sample efficiency for learning in the closed loop system. Additionally, approaches for efficient non-parametric online learning algorithms are proposed to allow the application of the presented methods under real-time constraints.