Enhanced Particle Swarm Optimization for UAV Path Planning

Metaheuristic algorithms have been widely utilized for solving multi-objective optimization problems (MOOPs) in recent years. Particle Swarm Optimization (PSO) has gained popularity among these algorithms due to its effectiveness in solving MOOPs. However, the performance of PSO highly relies on its exploration and exploitation abilities. The authors propose an enhanced PSO algorithm to address these limitations in this research paper. The study focuses on the initialization of the population, the incorporation of a random walk strategy, and the adaptive inertia weight parameter. The proposed algorithm utilizes a random initialization technique based on beta distribution. Additionally, a Brownian motion-based random walk strategy is incorporated to improve the algorithm’s convergence speed and accuracy. The results and discussions demonstrate that the enhanced PSO algorithm outperforms existing PSO variants in solving complex multi-objective optimization problems, specifically in the case of Unmanned Aerial Vehicle (UAV) path planning.