Roadronix: An AI-Based Semi-Autonomous System for Pothole Detection and Simulated Preemptive Road Repair

Road infrastructure maintenance is a critical challenge in urban environments, where potholes pose safety risks and raise operational costs. Existing pothole-detection systems mainly report road damage and provide no integrated repair mechanism, leaving a delay between identification and action. This paper presents Roadronix, an AI-based semi-autonomous system that detects potholes from image input, classifies their severity, selects a repair action through a rule-based decision engine, and simulates a step-by-step repair pipeline (aligning, filling, compacting, completion) during road preparation stages. The system offers AI and manual operating modes and a dashboard that reports detection counts, repair stages, and performance metrics. A simulation-based evaluation demonstrates the complete detection-to-repair workflow without physical hardware. The approach aims to shift road maintenance from a reactive to a proactive process.