Improved strategy based sparrow search algorithm for UAV 2D path optimization
Wanli Guo · 2024
In recent years, swarm intelligence optimization algorithms have demonstrated excellent performance in optimization, achieving favorable results in solving complex practical problems. Sparrow Search Algorithm (SSA) is an intelligent algorithm proposed in recent years. This paper focuses on the two-dimensional path optimization of Unmanned Aerial Vehicles (UAVs). Addressing issues such as the decline in population diversity and susceptibility to local optima in the later iterations of the Sparrow Search Algorithm, a multi-strategy hybrid improved Sparrow Search Algorithm (ISSA) is proposed. ISSA is applied to UAV two-dimensional path optimization planning to find the optimal path for obstacle avoidance. This paper utilizes Piecewise Linear Chaotic Mapping (PWLCM) to optimize the initial settings of the population, enhances population diversity, and effectively controls the balance between global search and local optimization using a nonlinear weight factor. This strengthens the algorithm's global optimization ability and avoids the algorithm from being trapped in local optima. Perturbation is introduced through longitudinal and transverse crossover strategies, introducing new genetic variations among population individuals to increase diversity, helping the algorithm escape local optima and find better solutions. Through multi-strategy improvements, a hybrid improved ISSA Sparrow Search Algorithm is formed. Simulation experiments demonstrate that ISSA outperforms five other algorithms including GA, SSA, PSO, DE, and GWO in terms of path optimization performance.