基于改进蚁群算法的AGV全局路径规划

AGV global path planning based on improved ant colony algorithm

目的:针对传统蚁群算法存在易陷入局部最优值、前期盲目搜索和收敛速度慢等问题,提出一种改进算法并应用于AGV(Automated Guided Vehicles)全局路径规划。方法:通过优化状态转移概率以及信息素更新方法完成对传统蚁群算法的改进;然后建立环境地图模型,并将改进算法应用于AGV路径规划;最后进行对比试验,并分析算法的改进效果。结果:与现有算法比较,改进算法可更快获得更短的规划路径长度,同时可有效减少算法迭代次数。结论:通过优化状态转移概率和信息素更新方法,可有效加快蚁群算法的收敛速度,增强蚁群全局搜索能力。

Objective:To propose an improved algorithm and apply it to the global path planning of AGV(Automated Guided Vehicles)to address the problems of traditional ant colony algorithm which is easy to fall into local optimum,blind search in the early stage,and slow convergence speed.Methods:The improvement of the traditional ant colony algorithm is completed by optimizing the state transfer probability and the pheromone updated method.The environment map model is established and the improved algorithm is applied to AGV path planning.The comparison experiment is conducted and the improvement effect of this algorithm is analyzed.Results:The improved algorithm can quickly obtain shorter planning path lengths,while effectively reducing the number of iterations of the algorithm,compared to the existing algorithm.Conclusion:By optimizing the state transfer probability and pheromone updated method,the convergence speed of the ant colony algorithm can be effectively accelerated and the global search capability of the ant colony can be enhanced.