Application of Improved PSO with Dynamic Inertia Weight Adjustment in 3D Path Planning of UAV
Lefan Zhang · 2025
With the increasing application of unmanned aerial vehicles (UAVs) in complex dynamic environments, path planning technology faces challenges such as slow convergence and easy to fall into local optimality. In view of the limitations of traditional particle swarm optimization (PSO) algorithm in three-dimensional path planning, this paper proposes an improved PSO algorithm with dynamic inertia weight adjustment. The algorithm balances global exploration and local development capabilities through a linearly decreasing inertia weight strategy, a larger inertia weight is used in the early stage of search to enhance the global search capability, and the weight is gradually reduced in the later stage to focus on local refined optimization. The three-dimensional simulation experiment verifies that the path generated by the improved algorithm is significantly better than the traditional PSO algorithm in terms of smoothness, obstacle avoidance ability and path length, and the convergence speed is increased by more than 6.7%. The experimental results show that the dynamic inertia weight strategy effectively reduces the sensitivity of the algorithm to the initial parameters and improves its robustness in complex dynamic environments. This study provides a new solution for the optimization of autonomous path planning algorithms for UAVs.