This paper discusses the optimisation of a fuzzy-neural controller based on the paradigm of genetic search. The controller under consideration is a hybrid one which can be interpretated as a Takagi/Sugeno model of fuzzy inference or a basis function network. The discretisation of the search space must be addressed, encoding methods for the fuzzy rulebase and the construction of a fitness evaluation procedure. The developed techniques are applied to the problem of lateral control of an autonomous vehicle based on a linearized time varying model of the vehicle s response to steering inputs. The performance of the control system is measured by a complex cost function combining both passenger comfort and security aspects which is minimised by changing the parameters and structure of a fuzzy-neural contoller.
Genetic-based optimisation of a fuzzy-neural vehicle controller
Optimierung einer neuronalen Fuzzy-KFZ-Steuereinrichtung auf der Basis genetischer Algorithmen
1994
13 Seiten, 7 Bilder, 20 Quellen
Conference paper
English
Optimisation of a fuzzy logic traffic signal controller by a multiobjective genetic algorithm
British Library Conference Proceedings | 1998
|A genetic fuzzy controller for vehicle automatic steering control
Tema Archive | 2007
|Genetic optimisation of a neural damage locator
Online Contents | 2008
|