改进蚁群算法的AGV自主避障  

Autonomous Obstacle Avoidance of AGV Based on Improved Ant Colony Algorithm

作　　者：苏莹莹[1] 李志宇 SU Yingying;LI Zhiyu(School of Mechanical Engineering,Shenyang University,Shenyang 110044,China)

机构地区：[1]沈阳大学机械工程学院,辽宁沈阳110044

出　　处：《沈阳大学学报（自然科学版）》2024年第4期289-296,340,共9页Journal of Shenyang University：Natural Science

基　　金：中央引导地方科技发展计划(2021JH6/10500149)。

摘　　要：针对传统蚁群算法在AGV任务调度效率的不足和避障问题,提出了一种改进的蚁群算法。首先,通过引入路径忙碌值,改进蚁群算法中的路径信息素浓度,提高路径规划解的质量;其次,对启发式的信息素浓度添加随机影响因子,进而提高算法的搜索效率。然后,在改进的蚁群算法基础上,引入路径多次规划参数和工作运行影响参数,并对AGV制定基本调度规则和任务优先级,提出一种综合的避障策略来解决冲突问题。仿真实验结果表明改进的蚁群算法可以评估路径使用率,进而规划最优的路径。在多任务调度效率上有明显优势,并能有效实现自主避障,解决碰撞问题。An improved ant colony algorithm was proposed to address the shortcomings of traditional ant colony algorithms in AGV task scheduling efficiency and path obstacle avoidance problems.First,by introducing the path busy value,the path pheromone concentration in the ant colony algorithm was upgraded to improve the quality of the path planning solution;Secondly,random influence factors were added to the heuristic pheromone concentration to improve the search efficiency of the algorithm.Then,based on the improved ant colony algorithm,multiple path planning parameters and work operation impact parameters were introduced,and basic scheduling rules and task priorities were formulated for AGV to propose a comprehensive obstacle avoidance strategy to solve the conflict problem.The simulation experimental results showed that the improved ant colony algorithm could evaluate path utilization and plan the optimal path.It had obvious advantages in multi task scheduling efficiency and could effectively achieve autonomous obstacle avoidance and solve collision problems.

关 键 词：调度效率 路径规划 自主避障 AGV 改进蚁群算法 

分 类 号：TH165[机械工程—机械制造及自动化] TP23[自动化与计算机技术—检测技术与自动化装置]