Design of Port Positions Based on Self-organizing Maps for Travel Path of Mobile Robots in a Logistics Warehouse

This study proposes an algorithm for optimizing port (loading points) placement in logistics warehouses to prevent collisions and improve mobile robot navigation. The proposed approach uses a self-organizing map (SOM) to iteratively adjust node positions and eliminate edge intersections in non-uniform planar graphs. A counter clockwise (CCW) algorithm ensures accurate intersection detection, while a maintain node distance (MND) algorithm prevents node overlap and enhances visual readability. Simulation results confirm that the approach effectively removes initial edge intersections and improves overall graph layout. This study proposes a novel framework for addressing non-uniform planar graph challenges with practical implications for warehouse automation and robot path optimization.