Modeling and intelligent control design of car following behavior in real traffic flow

Abstract

The control of car following is essential to its safety and its operational efficiency. For this purpose, this paper builds a linear, continuous and time-delay model of car following. And then, presents a controller based on an adaptive network fuzzy inference system (ANFIS) for the car-following collision avoidance system to adaptively control the speed of the vehicle. The relative distance and relative speed to the in front car are measured and are applied to the controller. The output acceleration or deceleration rate of the controller is based on the characteristics of the vehicles. The presented ANFIS controller can solve the problems of the oscillations for final distance between the leader vehicle (LV) and the follower vehicle (FV) and their relative speed. The designed ANFIS controller is linked to the car following model. The simulation results show that the ANFIS control design is more effective and can provide a safe, reasonable, and comfortable drive than real driver.