基于改进麻雀搜索算法的路径规划

Path Planning Based on Improved Sparrow Search Algorithm

麻雀搜索算法是一种新颖的群智能算法,具有寻优能力强、收敛速度快的优点,但存在易陷入局部最优等不足.提出改进麻雀搜索算法用于路径规划,通过动态调整发现者与追随者的选择阈值,结合随机保留策略,使麻雀种群的全局与局部搜索的边界可动态调整并随机地保留非最优个体,从而达到降低陷入局部最优的风险的目的.实验表明,该方法在路径规划中具有较强的鲁棒性和泛化能力,能够在多种随机复杂环境下获得安全且平滑性较好的路径.

The sparrow search algorithm is a novel swarm intelligence algorithm,which has the advantages of stronger optimization and faster convergence speed.However,it has some disadvantages such as falling into local optimum easily.An improved sparrow search algorithm is proposed for path planning.By dynamically adjusting the selected threshold for the discoverers and the followers,plus a random holding strategy,the global and local search boundaries of the sparrow population can be dynamically adjusted and held non-optimal individuals randomly to reduce the risk of falling into local optimization.Our experiments show that the method has strong robustness and generalization in path planning,and can obtain safe and smooth paths in random and complex environments.