Dynamic Weighted Spherical Particle Swarm Optimization for UAV Path Planning in Complex Environments

Path planning for Unmanned Aerial Vehicles (UAVs) in complex environments presents several challenges. Traditional algorithms often struggle with the complexity of high-dimensional search spaces, leading to inefficiencies. Additionally, the non-linear nature of cost functions can cause algorithms to become trapped in local optima. Furthermore, there is often a lack of adequate consideration for real-world constraints, for example, due to the necessity for obstacle avoidance or because of the restrictions of flight safety. To address the aforementioned issues, this paper proposes a dynamic weighted spherical particle swarm optimization (DW-SPSO) algorithm. The algorithm adopts a dual Sigmoid-based adaptive weight adjustment mechanism for balancing global exploration and local exploitation, as well as a lens-based opposition learning one to improve search flexibility and solution diversity. Simulation experiments on real digital elevation models demonstrate that DW-SPSO significantly outperforms recent state-of-the-art particle swarm optimization (PSO) variants in terms of path safety, smoothness, and convergence speed. The performance superiority is statistically validated by the Wilcoxon signed-rank test. The results confirm the algorithm’s effectiveness in generating high-quality UAV paths under diverse threat conditions, offering a robust solution for autonomous navigation systems.