Research on Particle Swarm Optimization-Based UAV Path Planning Technology in Urban Airspace

Urban airspace, characterized by densely packed high-rise buildings, presents complex and dynamically changing environmental conditions. It brings potential risks to UAV flights, such as the risk of collision and accidental entry into no-fly zones. Currently, mainstream path planning algorithms, including the PSO algorithm, have issues such as a tendency to converge to local optimal solutions and poor stability. In this study, an improved particle swarm optimization algorithm (LGPSO) is proposed to address these problems. This algorithm redefines path planning as an optimization problem, constructing a cost function that incorporates safety requirements and operational constraints for UAVs. Stochastic inertia weights are added to balance the global and local search capabilities. In addition, asymmetric learning factors are introduced to direct the particles more precisely towards the optimal position. An enhanced Lévy flight strategy is used to improve the exploration ability, and a greedy algorithm evaluation strategy is designed to evaluate the path more quickly. The configuration space is efficiently searched using the corresponding particle positions and UAV parameters. The experiments, which involved mapping complex urban environments with 3D modeling tools, were carried out by simulations in MATLAB R2023b to assess their algorithmic performance. The results show that the LGPSO algorithm improves by 23% over the classical PSO algorithm and 18% over the GAPSO algorithm in the optimal path distance under guaranteed security. The LGPSO algorithm shows significant improvements in stability and route planning, providing an effective solution for UAV path planning in complex environments.