作者：应仲谋1，孟冠军2
单位：1. 华侨大学机电及自动化学院, 福建厦门 361021；
      2. 合肥工业大学机械工程学院，安徽合肥 230009
中图分类号：TP28；TP23           
文献标识码：A           
文章编号：1006-883X(2020)08-0013-05
收稿日期：2020-06-07

摘要：AGV是车间物流的重要工具，其路径规划是实现车间物流自动化和智能化的核心。为提高AGV的避障和路径规划效率，首先利用可视图法建立问题的环境模型，据此采用两阶段算法进行最优路径搜索。第一阶段利用A*算法寻优速度极快的优点规划出一条较优的初始路径；第二阶段针对传统蚁群算法收敛速度慢且易陷入局部最优导致算法停滞的不足，采用一种新的改进蚁群算法高效地搜索出最优路径。最后将两阶段算法应用于实际案例，通过与传统蚁群算法的搜索结果加以对比，表明了两阶段算法搜索到的路径更优，验证了两阶段算法的有效性。
关键词：AGV；路径规划；A*算法；蚁群算法

Study On AGV Path Planning Based on Two-Stage Algorithm
YING Zhong-mou1, MENG Guan-jun2
1. College of Mechanical Engineering and Automation, Huaqiao University, Xiamen 361021, China; 2. School of Mechanical Engineering, Hefei University of Technology, Hefei 230009, China
Abstract: AGV is an important tool for workshop logistics, and its path planning is the core to realize automation and intelligence of workshop logistics. In order to improve the efficiency of obstacle avoidance and path planning, we first use the visibility graph to establish the environment model of the problem, and then two-stage algorithm is adopted to search the optimal path. In the first stage, A* algorithm which has the advantage of very fast searching speed is adopted to find a relatively good path. Aiming at the deficiency of the traditional ant colony algorithm, which is slow in convergence and easy to fall into the local optimum, we adopt a new improved ant colony algorithm to search the optimal path efficiently in the second stage. Finally, in order to verify the effectiveness, the two-stage algorithm is applied to a practical case, and compared with the results of the traditional ant colony algorithm. The test results show that the two-stage algorithm has a better path.
Key words: AGV; path planning; A*algorithm; ant colony algorithm

阅读全文

备注：2020年 第26卷 第08期