Abstract: For the shortcomings of easy to fall into the path deadlocks, an improved ant colony algorithm is proposed to plan the optimal collision-free path for a mobile robot in a complex environment. Firstly, grid model of the robot environment is established, and an array of element point to the previous is employed to enhance the escaping capability of algorithm. It utilizes the pheromone released by the worst ant to update the pheromone, which is conducive to the evolution of the colony. The main parameters’ influence on the performance of the algorithm is analyzed. Simulation results show that the optimal collision-free path on the complex map obtained by this algorithm is superior to the traditional algorithm.

Key words: mobile robot, path planning, ant colony algorithm, grids

摘要： 针对蚁群算法易陷入路径死锁的缺点，提出了一种复杂环境下移动机器人路径规划的改进蚁群算法。对机器人环境建立栅格模型，在传统转移规则中引入指向上一节点的数组，增强了算法的逃逸能力；在信息素更新中减去最差蚂蚁释放的信息量，有利于种群的进化。仿真分析了主要参数对算法性能的影响，实验结果表明，该算法在复杂地图中搜索到的路径优于传统算法。

关键词: 移动机器人, 路径规划, 蚁群算法, 栅格法