Dual-Layer Dynamic Path Optimization for Airport Ground Equipment Using Graph Theory and Adaptive Genetic Algorithms

With the continuous promotion of smart airport construction, the application of unmanned ground equipment vehicles in airports is becoming increasingly popular. The existing path planning methods rely on manual management, which has problems such as low efficiency and poor ability to respond to unexpected situations. Given this, this study first models the airport path based on graph theory. Secondly, a two-layer dynamic path optimization algorithm is designed by combining the improved dynamic programming Dijkstra algorithm with the introduced genetic algorithm for path conflict identification and avoidance mechanisms. Performance test results showed that the running time of the improved Dijkstra algorithm was shortened by about 48.29% and the number of edges was reduced by 10.07%. The fitness value and variance of the improved genetic algorithm increased by 8.99% and decreased by 66.67%, respectively. In a high-density and high-frequency conflict environment, the path success rate of the proposed model was 90.1%, which was 7.2% higher than the comparative algorithm. In addition, its path smoothness standard deviation was 5.32°, better than 6.68° and 8.47° of the comparative algorithms. The results indicate that the optimized path planning method can reduce the total running time and effectively avoid path conflicts between multiple vehicles, providing certain technical support and new ideas for the safe operation of airport special unmanned equipment vehicles.