MechE Colloquium: Safe Learning in Automatic Control Systems
Event details
| Date | 13.05.2022 |
| Hour | 12:00 › 13:00 |
| Speaker | Prof. Melanie Zeilinger, Department of Mechanical and Process Engineering, Institute for Dynamic Systems and Control, ETHZ |
| Location | Online |
| Category | Conferences - Seminars |
Face masks are recommended for in-person attendance in MED 0 1418.
Abstract: Automation is transforming our society through technological advances in robotics, transportation, manufacturing, energy and medical systems. As ubiquitous sensing and communication is turning these systems into large data generators, learning is becoming a central element of automatic control systems to address new levels of system complexity, variability and user interaction. While this paradigm shift offers tremendous opportunities, it also raises fundamental questions of learning in a closed-loop dynamical control system. The issue of safety is widely recognized as one of the key challenges limiting the widespread use of learning in industrial control applications.
In this talk, I will present our research towards a new class of controllers that enable even safety-critical systems to leverage the potential of data and to advance our understanding of their safety and performance properties. I will particularly highlight our results for using learning for automatic controller design to reduce development time while pushing the performance envelope, as well as a novel modular framework that can equip any learning-based controller with safety guarantees. The underlying theory and concepts will be illustrated with examples of applications from robotics.
Biography: Melanie Zeilinger is an Assistant Professor at the Department of Mechanical and Process Engineering at ETH Zurich, Switzerland where she leads the Intelligent Control Systems group. She received the Diploma degree in Engineering Cybernetics from the University of Stuttgart, Germany, in 2006, and the Ph.D. degree with honors in electrical engineering from ETH Zurich, Switzerland, in 2011. From 2011 to 2012 she was a Postdoctoral Fellow with the Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland. She was a Postdoctoral Researcher with the Max Planck Institute for Intelligent Systems, Tübingen, Germany until 2015 and with the Department of Electrical Engineering and Computer Sciences at the University of California at Berkeley, CA, USA, from 2012 to 2014. From 2018 to 2019 she was a professor at the University of Freiburg, Germany. Her awards include the ETH medal for her PhD thesis, a Marie-Curie IO fellowship and an SNF Professorship grant. She is one of the organizers of the new Conference on Learning for Dynamics and Control (L4DC). She is currently an Associate Editor for the IEEE Control Systems Magazine and the IEEE Control Systems Letters. Her research interests include learning-based control with applications to robotics and human-in-the-loop control.
Abstract: Automation is transforming our society through technological advances in robotics, transportation, manufacturing, energy and medical systems. As ubiquitous sensing and communication is turning these systems into large data generators, learning is becoming a central element of automatic control systems to address new levels of system complexity, variability and user interaction. While this paradigm shift offers tremendous opportunities, it also raises fundamental questions of learning in a closed-loop dynamical control system. The issue of safety is widely recognized as one of the key challenges limiting the widespread use of learning in industrial control applications.
In this talk, I will present our research towards a new class of controllers that enable even safety-critical systems to leverage the potential of data and to advance our understanding of their safety and performance properties. I will particularly highlight our results for using learning for automatic controller design to reduce development time while pushing the performance envelope, as well as a novel modular framework that can equip any learning-based controller with safety guarantees. The underlying theory and concepts will be illustrated with examples of applications from robotics.
Biography: Melanie Zeilinger is an Assistant Professor at the Department of Mechanical and Process Engineering at ETH Zurich, Switzerland where she leads the Intelligent Control Systems group. She received the Diploma degree in Engineering Cybernetics from the University of Stuttgart, Germany, in 2006, and the Ph.D. degree with honors in electrical engineering from ETH Zurich, Switzerland, in 2011. From 2011 to 2012 she was a Postdoctoral Fellow with the Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland. She was a Postdoctoral Researcher with the Max Planck Institute for Intelligent Systems, Tübingen, Germany until 2015 and with the Department of Electrical Engineering and Computer Sciences at the University of California at Berkeley, CA, USA, from 2012 to 2014. From 2018 to 2019 she was a professor at the University of Freiburg, Germany. Her awards include the ETH medal for her PhD thesis, a Marie-Curie IO fellowship and an SNF Professorship grant. She is one of the organizers of the new Conference on Learning for Dynamics and Control (L4DC). She is currently an Associate Editor for the IEEE Control Systems Magazine and the IEEE Control Systems Letters. Her research interests include learning-based control with applications to robotics and human-in-the-loop control.
Practical information
- General public
- Free