Enhancing Road Safety Through a Fuzzy-Based Adaptive Alert System for Critical Motorcycle–Car

Abstract

Ensuring safety in road traffic remains a critical challenge, particularly in scenarios involving motorcycles approaching the blind spot of larger vehicles. This paper proposes an intelligent, context-aware alert system based on Fuzzy Logic, capable of generating gradual warning signals to assist car drivers in anticipating potential collisions. Grounded in real-world accident data, the system integrates Responsibility-Sensitive Safety (RSS) equations with the ISO 17387 safety standard to define critical interaction zones. A custom simulation environment was developed using the CARLA platform, enabling realistic vehicle dynamics and sensor modeling. The proposed fuzzy controller processes longitudinal and lateral safety parameters, along with real-time inter-vehicle distance, to classify the level of danger and modulate the alert intensity accordingly. Unlike traditional binary systems, the fuzzy engine provides a continuous output ranging from low to high criticality, ensuring timely and non-intrusive driver assistance. Simulation results across nine accident-based scenarios demonstrate the system’s effectiveness in anticipating risks, minimizing false positives, and enhancing driver response time. This work contributes to a scalable, human-centric safety mechanism for Advanced Driver-Assistance Systems (ADAS), with strong potential for real-world application in environments involving mixed traffic and vulnerable road users.