Abstract

Aim: With cutting-edge technologies revolutionizing modern life, autonomous vehicles connected with in-frastructure applications are significantly impacting human life through technologies such as Vehi-cle-to-Everything (V2X), Vehicle-to-Infrastructure (V2I), and Vehicle-to-Vehicle (V2V). This paper pre-sents the state of the art in fuzzy models implementing adaptive cruise control (ACC) for vehicles and com-pares their respective results.
Methods: The demand for efficient automobile cruise control systems is on the rise. However, these systems are very complex and require an accurate model, which is difficult to achieve due to complex and variable road conditions. Therefore, reaching level 5 autonomous driving, which refers to a fully automated vehicle capable of performing all driving functions, will eventually require fuzzy logic inference to help incorporate human-like thinking into the vehicle.
Results: This paper investigates both current and previous research, comparing the overall performance of various fuzzy systems to non-fuzzy systems.
Conclusion: This paper presents various fuzzy logic cruise controllers aimed at improving and enhancing the autonomous driving experience. Among the methods reviewed are Fuzzy PID controllers, Fuzzy MPC with Type 1 and Type 2 using genetic algorithms, and fuzzy cooperative adaptive cruise control. The challenging problem of comparing different algorithms for fuzzy cruise control has been considered, studied, and ana-lyzed. The main conclusion of this comparative study is that applying different methods to the same adaptive cruise control system results in varying responses and output characteristics.

Key words: Adaptive Cruise Control; Fuzzy Control Systems; V2X; CACC; Fuzzy PID Controllers; A Comparative Study