Genetic Optimization of Fuzzy Adaptive Cruise Control for Urban Traffic - Fuzzy Modeling and Control: Theory and Applications - page 245

Fig. 14.1 Full block diagram used for the tuning of the fuzzy controller by means of simulation
the controller (Herrera et al. 1995 ). Either all the parameters of the controller can be
automatically tuned, or only some of them.
In this work a Genetic Algorithm is used for the tuning of some of the parameters
of a fuzzy controller for the accelerator and brake pedals of a car, by means of
simulations. The remaining parameters are manually configured.
The rest of the chapter is organized as follows: the mathematical model used in
the simulations, which includes the vehicle ahead, the sensory system, the controller
and the vehicle controlled, is described in Sects. 14.2 and 14.3 a short description of
the genetic algorithm used is given; in Sect. 14.4 the results obtained are presented;
finally, in Sect. 14.5 some conclusions are given.
14.2 Mathematical Model
Figure 14.1 shows the block diagram of the complete system used in the simulations.
The vehicle being followed, the sensory system, the controller and the car controlled
can be seen. The blocks are described below.
14.2.1 Pursued Car
This block provides the temporal position of the car ahead. Its speed varies between
0 and 50Km/h, which is the maximum speed allowed in urban traffic in Spain.
14.2.2 Sensors
Simulates the sensory system used by the controller, which provides the distance
between vehicles and the speed of the car controlled every 0.1 s.
Since in this work the region of interest is limited to 15m ahead of the controlled
vehicle, this sensor saturates at this distance. In the same way, the speed measured
becomes saturated at 50Km/h, because of the reason given above.