Robust Road Condition Detection System Using In-Vehicle Standard Sensors.

Area of Science:

• Automotive Engineering
• Road Safety Technology
• Artificial Intelligence in Vehicles

Background:

• Active safety systems (e.g., Anti-lock Braking System, Traction Control System, Stability Control System) are crucial for road safety.
• These systems require accurate road condition data for optimal performance.
• Current systems often lack real-time road condition detection capabilities.

Purpose of the Study:

• To develop a method for detecting road conditions using standard sensors in commercial vehicles.
• To enable vehicle control systems to adapt proactively to detected road surfaces.
• To enhance the effectiveness of active safety systems through real-time environmental awareness.

Main Methods:

• Vehicle models were programmed into on-board systems to estimate wheel-road contact forces and vehicle speed.
• A fuzzy logic block was implemented to generate a road condition index.
• An artificial neural network was utilized to determine optimal slip control for various surfaces.

Main Results:

• The proposed method successfully detects road conditions using existing vehicle sensors.
• Real-time estimation of forces and speed allows for accurate road surface characterization.
• The fuzzy logic and neural network approach provides optimal slip control for different conditions.

Conclusions:

• The developed system effectively detects road conditions, improving active safety system responsiveness.
• This technology offers a significant advantage in preventing accidents by enabling faster and more suitable vehicle control.
• The method is validated through simulations and experimental tests, demonstrating its practical applicability.