Guest lecture: Learning Control for Complex Mechatronic Systems Using Model-free and Model-based Methods as Applied to Robotics and Intelligent Vehicles

Assistant Prof. Erdal Kayacan, Nanyang Technological University, Singapore.

11.09.2017 | Anja Torup Hansen

Dato tor 14 sep
Tid 13:15 14:15
Sted Room 120E, building 5125, Finlandsgade 22, 8200 Aarhus N

Abstract
Controller design is more troublesome in complex mechatronics and robotic systems due to, inter–alia, having more than one subsystem, diversity of mission platforms, convoluted nonlinear dynamics, predominantly strict mission and resource constraints as well as demands for guaranteed operability within a wide range of operating conditions that can undergo structural or unexpected changes. Request for increased, almost perfect, accuracy and efficiency of robotic systems, e.g. intelligent vehicles, pushes the operation to the boundaries of the performance envelope and, thus, induces a need for reliable operation at the very limits of attainable performance. In model-based control, control accuracy highly depends on the representativeness of the model describing the system behaviour. On the other hand, in real life, information one can learn from a system is always uncertain and limited in scope due to the noise from both inside and outside of that system as well as the limitations of our cognitive abilities. Even if an accurate model of the system is available, control system encounters various environmental conditions (such as humidity, temperature, etc.). These time varying working conditions might decrease the control accuracy or even lead overall control system to instability when a conventional controller, e.g. a proportional-integral-derivative (PID) controller, is used. Since conventional controllers do not have the ability of adapting themselves to changing conditions, they are not suitable to be used in such changing working conditions. The use of advanced learning algorithms, which can learn the operational dynamics online and adjust the operational parameters accordingly, might be a candidate solution to all the aforementioned problems. This seminar will focus on model-free and model-based control and learning methods using type-1 and type-2 fuzzy neural networks and model predictive control-moving horizon estimation framework to handle various real-time problems. Furthermore, a few real-time implementations, e.g. guidance and control of autonomous ground vehicles and vision-based control of unmanned aerial vehicles, will also be demonstrated.
 

Erdal Kayacan holds a PhD in Electrical and Electronic Engineering from Bogazici University (2011).  He was a visiting scholar at the University of Oslo at the Department of Informatics in Robotics and Intelligent Systems (ROBIN) Group in 2009 with the research fellowship of Norway Research Council. After his post-doctoral research in University of Leuven (KU Leuven) at the Division of Mechatronics, Biostatistics and Sensors (MeBioS), Dr. Kayacan went on to pursue his research in Nanyang Technological University at the School of Mechanical and Aerospace Engineering as assistant professor (2014 – current). He has since published more than 85 peer-refereed book chapters, journal and conference papers in model-based and model-free control, parameter and state estimation, and their robotics applications.  He has attracted around 3,6 million SGD (16million Danish Krone) as principal investigator in the last three years. His current research projects focus on the design and development of ground and aerial robotic systems, vision-based control techniques and artificial intelligence. Dr. Kayacan is co-writer of a course book “Fuzzy Neural Networks for Real Time Control Applications, 1st Edition Concepts, Modeling and Algorithms for Fast Learning”. He is a Senior Member of Institute of Electrical and Electronics Engineers (IEEE). Since 1st Jan 2017, he is an Associate Editor of IEEE Transactions on Fuzzy Systems, the leading international journal in his main research field.

Forelæsning / foredrag