Unmanned Aerial Vehicle Path Planning Based on Inverse Learning Strategy Particle Swarm Optimization Algorithm

This paper proposes an improved particle swarm optimization (PSO) algorithm based on opposition-based learning mechanism for UAV path planning. The algorithm incorporates constraints including terrain threats, radar threats, UAV turning angle, maximum flight distance, and flight altitude. The integration of elite opposition-based learning strategy enhances the algorithm's search efficiency and global optimal solution discovery capability. Simulation results demonstrate that the improved algorithm outperforms the basic PSO in both path planning accuracy and computational time, achieving faster convergence while effectively balancing multi-objective optimization problems. Consequently, it generates superior flight paths for UAVs.