融合遗传算法与蚁群算法的机器人路径规划

Path Planning of Robot by Integrating Genetic Algorithm and Ant Colony Algorithm

针对传统蚁群算法在全局静态环境下,搜寻一条由起点到终点的最优路径时,初始信息素缺乏、易陷入局部最优且收敛速度差的问题,提出一种遗传算法和蚁群算法结合求解路径规划问题的方法。首先,利用栅格法建立机器人行走环境模型;其次,为解决蚁群算法初始信息素缺乏的问题,对遗传算法每次迭代得到的种群根据适应度进行排序,利用截断选择,选取种群前50%的较优个体,利用初始信息素产生规则来设置蚁群算法所需的初始信息素;设计控制策略,控制遗传算法向蚁群算法的转换时间;最后,利用蚁群算法搜索路径,根据信息素更新策略更新信息素,采用简化操作优化路径,使得路径更平滑且距离更短。仿真结果表明,该算法在增强全局搜索能力以及加快收敛速度方面有较好的改善。

When traditional ant colony algorithm searches for an optimal path from the starting point to the end point in a global static environment, there are problems such as lack of initial pheromone, easy to fall into local optimum and poor convergence speed. Therefore, a method combining genetic algorithm and ant colony algorithm for solving the path planning problem is proposed. Firstly, the model of robot walking environment is established by using the grid method. Secondly, in order to solve the problem of lack of initial pheromones in ant colony algorithm, the population obtained by each iteration of genetic algorithm is sorted according to fitness. Truncation selection is used to select the optimal individuals in the first 50% of the population, and the initial pheromone generation rules are used to set the initial pheromones required by ant colony algorithm. Control strategy is designed to control the conversion time from genetic algorithm to ant colony algorithm. Finally, the ant colony algorithm is used to search the path, update the pheromone according to the pheromone updating strategy, and simplify the operation to optimize the path, making the path smoother and shorter. The simulation shows that the proposed algorithm can enhance the global search capability and speed up the convergence.