基于改进蚁群算法的AGV路径规划研究

Research on AGV Path Planning Based on Improved Ant Colony Algorithm

近年来,自动导引机器人(AGV)一直是研究的热点问题,其中复杂路径规划为研究重点。为了更好地规划机器人路径,提出一种改进蚁群算法,该算法在传统蚁群算法基础上充分利用了MMAS算法的特点。首先,构建网格环境模型,引入算法概率函数和抑制因子,通过改变算法的启发式信息,加快算法收敛速度;其次,引入回退机制解决死锁问题,再将MMAS蚂蚁系统转化为局部扩散信息素,只有迭代试验的最优解才能加入到信息素更新中;最后,有效限制信息素浓度,避免发生搜索路径过早收敛现象。仿真实验结果表明,改进蚁群算法与传统蚁群算法相比,迭代次数减少45.6%,时间缩短46.2%,改进蚁群算法收敛速度更快、效率更高。

In recent years,automatic guided robot(AGV)has been a hot research topic,among which the complex path planning has always been the focus of research. In order to better plan the robot path,this paper proposes an improved ant colony algorithm. Based on the traditional ant colony algorithm,the improved ant colony algorithm makes full use of the characteristics of MMAS algorithm.Firstly,the grid environment model is constructed,and the algorithm probability function and inhibition factor are introduced to accelerate the convergence speed of the algorithm by changing the heuristic information of the algorithm. Secondly,the backoff mechanism is introduced to solve the deadlock problem,and then the MMAS ant system is transformed into a local diffusion pheromone. Only the optimal solution of the iterative experiment can be added to the pheromone update. Finally,the pheromone concentration is effectively limited to avoid premature convergence of search path. The simulation results show that compared with the traditional ant colony algorithm,the number of iterations is reduced by 45.6% and the time is reduced by 46.2%. It is proved that the improved ant colony algorithm has faster convergence speed and higher efficiency.