Logical Road Network Generation in a Hybrid Vision-Graph Approach

Road networks in a locality can be fully planned or fully unplanned. It can even be a mixture of both. New roads to be made need to accommodate existing structures and should also account for future structures or areas that will be built. However, manual planning might sometimes result in suboptimal road structures, as measured by vegetation plantability and road width. The system we propose takes into consideration the metrics that have been mentioned through a rule-based road network generation system that uses Minimum Spanning Trees and the A* algorithm. Unlike existing deep learning-based models, our rule-based approach is explainable and focuses on efficient road network generation instead of mimicking existing networks. The proposed method maintains identical paths while achieving faster runtime by completing generation in 49.45%, 25.93%, and 86.69% the time the baseline Dijkstra’s Algorithm takes for primary, secondary, and connector roads, respectively (84.92% overall). The resulting network provides a valuable reference for planning road networks in both real-world applications and simulation environments.