Adaptive cruise control based on fuzzy logic for collision avoidance in autonomous vehicles

Abstract

Intelligent adaptive cruise control (IACC) systems have become a key technology for enhancing the safety and reliability of autonomous vehicles operating in dynamic traffic environments. This study proposes a fuzzy logic-based IACC architecture for collision avoidance that integrates longitudinal speed control, lateral steering control, obstacle detection, safety distance assessment, rollover prevention, and emergency braking into a unified decision-making framework. Given the high cost and complexity associated with full-scale vehicle experiments, the proposed system was implemented and validated within a MATLAB®/Simulink® environment, utilizing a dynamic model based on the real-world characteristics of a commercial passenger vehicle. The controller continuously estimates the distance to surrounding obstacles, assesses the vehicle's dynamic state, and autonomously selects the safest maneuver—coordinating lane-change and emergency braking actions while accounting for vehicle stability and passenger comfort. Three representative driving scenarios, featuring obstacles of varying sizes and positions, were designed to evaluate the controller under realistic operating conditions. Simulation results demonstrated a 99.9% success rate in collision avoidance, smooth trajectory tracking, stable speed regulation, effective rollover prevention via lateral acceleration monitoring, and reliable emergency braking in critical situations. These results demonstrate that the proposed fuzzy logic-based IACC architecture offers a robust and effective solution for autonomous collision avoidance by integrating multiple safety-oriented control strategies into a single intelligent framework. Furthermore, the proposed approach provides a promising foundation for future experimental validation and real-world implementation in autonomous vehicles.