Performance Evaluation of an Integrated Fuzzy-Based Driving-Support System for Real-Time Risk Management in VANETs

Area of Science:

• Intelligent Transportation Systems
• Artificial Intelligence in Automotive Safety
• Fuzzy Logic Control Systems

Background:

• Autonomous vehicle development faces significant challenges, necessitating near-term driving-support solutions.
• Existing driver-assistance systems are evolving, but advanced safety measures are crucial.
• Vehicular Ad hoc Networks (VANETs) show potential to enhance driving-support technologies.

Purpose of the Study:

• To propose and implement an integrated, non-intrusive fuzzy-based driving-support system.
• To detect risky driving situations in real-time and alert drivers.
• To improve driving safety by managing hazardous conditions.

Main Methods:

• Utilized a fuzzy-based system for real-time risk detection.
• Integrated data from in-car sensors, vehicle-to-vehicle (V2V), and vehicle-to-infrastructure (V2I) communications.
• Analyzed parameters including driver health, in-car environment, vehicle speed, weather, and road conditions.

Main Results:

• Demonstrated the system's ability to evaluate driving risk levels based on diverse parameters.
• Showcased how identified risk levels can be translated into actionable alerts for drivers.
• Validated the system's effectiveness through simulations and experiments.

Conclusions:

• The proposed system effectively enhances driving safety by providing real-time risk assessment and alerts.
• It can operate as a stand-alone system or benefit from VANET advancements.
• This approach offers a practical solution for improving road safety in the near future.