An optimal path planning method for urban smart transportation vehicles

To address the challenges of extended distances and prolonged travel times in urban vehicle routing, an optimized path planning method using a Non-dominated Sorting Genetic Algorithm (NSGA) is proposed for intelligent transportation systems. The process begins with transportation vehicle travel information data and normalizing it after preprocessing. Subsequently, a multi-objective function and constraints are formulated to accommodate time windows and dynamic conditions for optimal vehicle routing. The NSGA is then employed to encode chromosomes, sort non-domination levels, and perform crossover and mutation operations. The algorithm is refined using crowding distance to generate the next generation population, ultimately integrating service satisfaction to determine the most favorable route. Experimental results demonstrate that this approach can significantly reducing both path length and total travel time.