Skip to Content

Search: {{$root.lsaSearchQuery.q}}, Page {{$}}

Learning Supported Predictive Control of Autonomous Systems

Rolf Findeisen, University Magdeburg, Germany
Friday, August 17, 2018
2:00-3:30 PM
Classroom 1012 Francois-Xavier Bagnoud Building Map
Learning Supported Predictive Control of Autonomous Systems

Rolf Findeisen
Laboratory for Systems Theory and Automatic Control Otto-von-Guericke
University Magdeburg, Germany

Due to rapid advancements in communication and information technology systems increasingly exchange information with neighboring systems or systems in the cloud. Examples are smart grids, production systems or multi-modal transportation systems. While the interconnections provide many fascinating possibilities, they also pose several challenges. What are suitable scalable control and monitoring technologies, which facilitate autonomy, plug and play operation while leading to an overall optimal behavior? How can such approaches be combined with methods from machine learning to cope with uncertainties? In the first part of this talk, we outline how contract based predictive control strategies allow a modular design of complex systems which facilitates hierarchical as well as decentralized autonomous operation of systems. The second part focuses on the fusion of learning approaches and predictive control methods to allow for adaptation in a changing environment. We consider the use of Gaussian Processes to learn model uncertainties and disturbances as well as the use of model predictive control and learning when the controlled system is subject to several possible, yet unknown modes. The presented methods are underlined by examples from robotics, autonomous driving, and air conditioning systems.

About the Speaker:

Rolf Findeisen obtained an M.S. degree from the University of Wisconsin, Madison, a Diploma in Engineering Cybernetics and Doctorate from the University of Stuttgart. Since 2007 he is heading the Laboratory for Systems Theory and Automatic Control at the Otto-von-Guericke Universit├Ąt Magdeburg. Rolf is editor/associated editor of several journals including the IEEE Transactions on Control of Network Systems and he is the international program co-chair of the IFAC World Congress 2020 in Berlin. The research of his group focuses on optimal and predictive control, control for autonomous systems, learning and control, decision-making under uncertainty, and network controlled systems. The considered fields of applications span from biotechnology, process automation, chemical processes, automotive applications and robotic, systems medicine.
Building: Francois-Xavier Bagnoud Building
Event Type: Lecture / Discussion
Tags: Engineering
Source: Happening @ Michigan from Aerospace Engineering