Abstract: In this paper，the link graph is used to describe the working space of the mobile robot and the Dijkstra algorithm is used to obtain a sub-optimal collision-free path from the start point to the goal point in the graph，then adopt the AFSA（Artificial Fish-Swarm Algorithm） to adjust and optimize the location of the sub-optimal path so as to generate the global optimal path by adjusting the points of the path.A calculation for an example has been done and the computation result shows that this method has some advantages as convergence and computation precision.

Key words: Artificial Fish-Swarm Algorithm（AFSA）, optimal path, path planning, robot

摘要： 首先采用链接图建立机器人工作空间模型，用Dijkstra算法求得链接图最短路径；然后使用人工鱼群算法对此路径进行优化，最终得到全局最优路径。以一个路径为例，进行了实际编程计算，结果表明，基于人工鱼群算法的机器人路径规划方法，具有较快的收敛性和较高的计算精度。

关键词: 人工鱼群算法, 最优路径, 路径规划, 机器人