An ANFIS controller for the car-following collision prevention system

Abstract

This paper presents a controller based on an adaptive network fuzzy inference system (ANFIS) for the car-following collision prevention system to nonlinearly control the speed of the vehicle. The distance and speed relative to the car in front are measured by a radar sensor and applied to the controller. The output acceleration or deceleration rate of the controller is based on the characteristics of the vehicles. The initial input and output membership functions and 25 rules of ANFIS are constructed by a fuzzy inference system (FIS). The design method of the reference signals, which is used to update on-line the consequent parameters of ANFIS according to recursive least square (RLS) algorithm, are proposed. The presented ANFIS controller can solve the problems of the oscillations for final distance between the leading vehicle (LV) and the following vehicle (FV) and relative speed. The required processing time to achieve safe distance between the LV and the FV is about 7-8 s, which is faster than the other models. The ANFIS controller of the car-following collision prevention system proposed in this paper can provide a safe, reasonable, and comfortable drive.