基于改进粒子群的混合金豺优化算法的移动机器人路径规划

Hybrid golden jackal optimization algorithm based on improved PSO for mobile robot path planning

针对金豺优化(Golden Jackal Optimization,GJO)算法在移动机器人路径规划应用中的迭代效率低以及会陷入局部最优等问题,提出一种改进粒子群的混合金豺优化(Hybrid Golden Jackal Optimization,HGJO)算法。首先,将自适应动态权重因子和改进的学习因子引入粒子群算法,以增强其全局探索能力;然后,建立机器人路径规划所需的栅格环境地图,并在此基础上将改进后粒子群算法引入金豺优化算法的位置更新过程,以改善GJO算法跳出局部最优的性能。由移动机器人的路径规划仿真实验可知,提出的HGJO算法在提升收敛速度和跳出局部最优性能方面均优于GJO算法,且在稳定性上优于粒子群算法。

In this paper,a hybrid golden jackal optimization(HGJO)based on improved particle swarm optimization(PSO)is proposed to address the problems of low iterative efficiency and falling into local optimality in the application of golden jackal optimization(GJO)to path planning of mobile robots.First,the new approach introduces adaptive dynamic weighting factors and refined learning factors into the PSO algorithm,thereby enhancing its capacity for global exploration.Then,the raster environment map required for robot path planning is established,based on which the improved particle swarm algorithm is introduced into the position update of the golden jackal optimization algorithm to improve the performance of the GJO algorithm in jumping out of the local optimum.Finally,the path planning simulation experiments of the mobile robot show that the proposed optimization algorithm outperforms the golden jackal optimization algorithm in terms of convergence speed and the ability to jump out of the local optimum;it outperforms the particle swarm algorithm in terms of stability.