Automated Transportation Asset Inventory System Using Self-Drive, Drones, and AI for Optimized Pavement Maintenance Management

This study presents a comprehensive model for automating transportation asset inventory and pavement marking maintenance using a synergistic approach that incorporates GPS-enabled self-driving vehicles, drones with pre-programmed routes, Artificial Intelligence (AI), and the European GRASP optimization algorithm. By integrating advanced imaging techniques, such as LiDAR and high-resolution cameras, with AI-driven data processing, the system enables high-frequency, high-precision asset detection, condition classification, and optimized maintenance scheduling. The proposed framework addresses the inefficiencies of current manual and semi-automated practices, introducing predictive analytics for proactive maintenance planning. Integration with Geographic Information Systems (GIS), machine learning, and control chart methods, including Shewhart algorithms, allows for real-time monitoring and decision support. The study highlights significant potential benefits, including reduced inspection costs and time, enhanced road safety, and improved compliance with visibility and reflectivity standards. While implementation challenges such as high initial costs and institutional adaptation exist, the modular, scalable design offers substantial operational and safety advantages for state and national transportation agencies.