Tire–Road Friction Estimation and Classification Based on a CNN using Tire Acoustical Signals for Autonomous Driving Vehicles

Advanced driver assistance systems (ADASs) and driving automation system technologies have significantly increased the demand for research on vehicle-state recognition. However, despite its critical importance in ensuring accurate vehicle-state recognition, research on road-surface classification remains underdeveloped. Accurate road-surface classification and recognition would enable control systems to enhance decision-making robustness by cross-validating data from various sensors. Therefore, road-surface classification is an essential component of autonomous driving technologies. This paper proposes the use of tire–pavement interaction noise (TPIN) as a data source for road-surface classification. Traditional approaches predominantly rely on accelerometers and visual sensors. However, accelerometer signals have inherent limitations because they capture only surface profile properties and are often distorted by the resonant characteristics of the vehicle structure. Similarly, image-based signals are susceptible to external factors such as lighting conditions, obstacles, and motion blur, which can compromise their reliability. In contrast, TPIN signals offer a more comprehensive representation of both the surface profile and texture characteristics of the road. Additionally, TPIN signals are less susceptible to environmental interferences that affect image-based methods. The TPIN signals are transformed into two-dimensional images using time–frequency analysis. These transformed images are subsequently utilized in conjunction with a convolutional neural network (CNN) architecture to evaluate the feasibility of a robust road-surface classification system. The system was implemented using MATLAB Simulink. Furthermore, this study explored the application of CNN-based artificial intelligence techniques to predict the tire–road friction coefficients across various road surfaces, providing a deeper understanding of the underlying principles governing tire–road interactions.