【摘要】 针对基本遗传算法在机器人路径规划中存在收敛速度慢、易陷入局部最优解的问题,提出一种改进的遗传算法.在适应度函数中增加带有惩罚项的平滑度函数;引入精英保留机制,保留每一代最优个体;自适应调整交叉概率和变异概率,使交叉概率和变异概率随进化次数变化而变化.利用MATLAB在两种障碍物地图中与其他两种算法进行仿真对比分析,实验结果表明,改进后的算法在路径规划的应用中有效减少了机器人的转弯次数,提高了逃离局部最优路径的能力,寻优能力更强.更多还原

【Abstract】 An improved genetic algorithm is proposed to solve the problem of slow convergence rate and easy to fall into the local optimal solution in robot path planning. The smoothness function with penalty term is added to the fitness function. The elite retention mechanism is introduced to retain the optimal individual of each generation. The crossover probability and mutation probability are adjusted adaptively so that they vary with the number of evolutions. MATLAB is used to simulate and compare the two obstacle maps with the other two algorithms. Experimental results show that the improved algorithm effectively reduces the number of turns of robots in path planning,improve the ability to escape from the local optimal path,and has a stronger ability to find the optimal solution.更多还原