针对基本遗传算法解决移动机器人路径规划问题存在收敛速度慢等不足,对遗传算法进行了改进,提出了一种改进自适应遗传算法。根据进化过程中个体适应度值的大小自动调节交叉概率和变异概率,从而使算法能够跳出局部最优解,克服早熟的缺点。同时采用栅格法对机器人工作空间进行建模。对移动机器人路径规划进行仿真实验,对比结果表明:该改进的遗传算法是有效可行的,能够有效的提高机器人路径规划的质量。
In order to deal with the problem such as slow convergence speed etc. of basic genetic algorithm formobile robot path planning, an improved adaptive genetic algorithm is proposed. This algorithm can adjust thecrossover probability and mutation probability automatically according to the change of the fitness value in theevolutionary process, thus to avoid falling into local optimal solution and overcome the shortcoming of prematurity.Meanwhile, the grid method is used to model the robot working space. The simulation for mobile robot path planningis performed and the comparison results show that this method is valid and the quality of robot path planning can beimproved effectively by using the proposed genetic algorithm.