GAforPathPlaning

代码说明：

说明：  采用栅格对机器人的工作空间进行划分，再利用优化算法对机器人路径优化，是采用智能算法求最优路径的一个经典问题。目前，采用蚁群算法在栅格地图上进行路径优化取得比较好的效果，而利用遗传算法在栅格地图上进行路径优化在算法显得更加难以实现。 利用遗传算法处理栅格地图的机器人路径规划的难点主要包括：1保证路径不间断，2保证路径不穿过障碍。 用遗传算法解决优化问题时的步骤是固定的，就是种群初始化，选择，交叉，变异，适应度计算这样，那么下面我就说一下遗传算法求栅格地图中机器人路径规划在每个步骤的问题、难点以及解决办法。(It is a classical problem to divide the workspace of the robot by grids and optimize the path of the robot by using optimization algorithm. At present, the ant colony algorithm is used to optimize the path on the grid map, and the genetic algorithm is used to optimize the path on the grid map, which is more difficult to achieve. The difficulties of using genetic algorithm to deal with the path planning of robot on raster map mainly include: 1. guaranteeing that the path is uninterrupted, 2. guaranteeing that the path does not cross obstacles. The steps of genetic algorithm in solving optimization problems are fixed, that is, population initialization, selection, crossover, mutation, fitness calculation. Then I will talk about the problems, difficulties and solutions of genetic algorithm in each step of robot path planning in raster map.)

文件列表：

GAforPathPlaning\cal_path_smooth.m, 1361 , 2019-01-10
GAforPathPlaning\cal_path_value.m, 749 , 2018-12-17
GAforPathPlaning\crossover.m, 1014 , 2019-01-10
GAforPathPlaning\DrawMap.m, 335 , 2019-01-10
GAforPathPlaning\generate_continuous_path.m, 3632 , 2018-12-17
GAforPathPlaning\main.m, 4401 , 2019-01-10
GAforPathPlaning\mutation.m, 1257 , 2018-12-17
GAforPathPlaning\selection.m, 566 , 2018-12-17
GAforPathPlaning, 0 , 2019-01-12