|
|
Fuzzy Models of Driver Behaviour
Fišer, Michal ; Mihálik, Ondrej (referee) ; Jirgl, Miroslav (advisor)
The master's thesis is concerned with finding a suitable fuzzy model for approximating data series representing driver's control interventions during lane changes. Firstly, the theoretical part presents an introduction to driver modelling and human-machine systems, the basics of fuzzy logic, fuzzy systems and controllers, optimization methods and a vehicle driving simulator. The thesis focuses mainly on McRuer models of human operator behaviour in~the area of driver behaviour modelling and genetic algorithms in~the area of optimisation methods. Based on this theory, individual linear models of driver behaviour are subsequently developed. The data were collected on a vehicle driving simulator. On this simulator, several experiments were conducted to measure the driver's response to a step change. Subsequently, the individual driver models were identified from the measured data using the System Identification Toolbox in Matlab. Furthermore, the design of a suitable fuzzy model structure is described. This is followed by~a~description of the genetic algorithm used to identify the fuzzy model and finally the~linear and fuzzy models are compared.
|
guest ::
