期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2013
卷号：57
期号：1
出版社：Journal of Theoretical and Applied
摘要：Vehicle automation for rear end collision avoidance during vehicle following is an area of research for the past few decade. For Adaptive cruising of vehicles, various controllers have been developed like PI, PID, Model predictive, Sliding mode control, which depend upon the system mathematical model. Designing such a mathematical model for nonlinear system with multiple parameters may not be easy. A controller which can emulate the behaviour of the human, and mimics their reaction which does not require the mathematical modeling of the system may be of high repute. One such controller is Fuzzy Logic controller (FLC). FLC does not need an exact mathematical representation of the system which is to be controlled. The performance of the FLC depends upon how well the fuzzy rule base is framed. The problem with FLC-based system is that, the number of rules used. The rule increases exponentially with the increase of the number of membership values that involve in the rules. This increase, leads to the rise in the computation time of the controller. However the performance of the FLC system highly relies upon the number of membership values and the rules. The crisp output of the FLC does not depend upon the best rule rather it depends upon the entire rule which gets qualified. In-order to have the best rule fired, Genetic Algorithm (GA) is used to optimise the rule base of FLC. Whenever Genetic Algorithm (GA) is used in real time optimisation of fuzzy rule base, the time for reaching the optimised value, depends upon the population size (number of rules in the fuzzy rule base). Hence for a time crucial application like Adaptive cruise control (ACC), offline tuning of fuzzy rule base is performed. In this paper new approach of segmented / divided fuzzy logic based controller is proposed where all the FLC used in ACC is tuned offline using GA and the performance comparison is made.
关键词：Adaptive Cruise Control; Fuzzy rule base optimisation; Genetic algorithm; Vehicle following
