Adaptive Position Updating Particle Swarm Optimization for UAV Path Planning

In the paper, we propose a path planning method for unmanned aerial vehicles (UAVs) based on an enhanced Particle Swarm Optimization (PSO) algorithm. To address the issue of classical PSO algorithms easily converging to local optima, we introduce a dynamic inertia weight adjustment strategy. Additionally, we incorporate Tent mapping initialization, Levy flight, and adaptive t-distribution to balance both global and local search capabilities. We validate the effectiveness of the improved algorithm through simulations on various benchmark functions and UAV path planning scenarios. Experimental results demonstrate significant enhancements in convergence speed, overall solution accuracy, and stability. Our improved PSO algorithm provides effective solutions for diverse UAV path planning problems in complex environments and lays the foundation for further research on dynamic environments and three-dimensional path planning in future.