<p>Amidst the swift progress of Industry 4.0, artificial intelligence (AI) and wireless IoT connectivity, these emerging technologies have contributed significantly to the development of effective new technological applications in society. Research on applying these Industry 4.0 technologies to automate the quality management of road infrastructure offers numerous benefits, such as enhancing the operational efficiency of transportation networks and improving traffic safety for road users. Automatic road surface damage detection is a critical component of the broader problem of detecting, locating, and reporting infrastructure damage to managers within intelligent road infrastructure management software systems. This paper presents an applied YOLOv8-based system for pavement damage detection, featuring a localized large-scale dataset, systematic hyperparameter optimization, and real-world deployment validation. The research results demonstrate that the automatic damage detection function effectively addresses limitations found in existing methods, achieving an average mean Average Precision (mAP) of 83.4% across all four damage types, with individual damage classes achieving mAP values exceeding 97.2%. The published data is validated and compared with measurements and accuracy assessments conducted by local traffic management agencies. By incorporating the latest knowledge and trends, this research offers an innovative global automation framework that delivers practical applications for traffic authorities and other technical managers. The findings highlight the potential of Industry 4.0 technologies as a powerful and adaptable approach to intelligent road infrastructure management, reducing time and costs associated with road management projects while contributing to infrastructure sustainability.</p>