Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (22): 67-70.

• 学术探讨 • Previous Articles     Next Articles

Improved genetic algorithm for robotic path planning

TANG Guo-xin,CHEN Xiong,YUAN Yang   

  1. School of Information Science and Technology,Fudan University,Shanghai 200433,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-08-01 Published:2007-08-01
  • Contact: TANG Guo-xin

机器人路径规划中的改进型遗传算法

唐国新,陈 雄,袁 杨   

  1. 复旦大学 信息学院,上海 200433
  • 通讯作者: 唐国新

Abstract: An improved genetic algorithm designed for robotic path planning is proposed.Crossover operator and mutation operator are specifically optimized for the application of path planning,and two customized genetic operators are introduced as well.The evolutionary efficiency is noticeably enhanced by incorporating map information in genetic operators and better adaptive ability towards complex maps is realized by adopting the customized genetic operators.Demonstrated by simulation results,the proposed algorithm achieves considerable improvements,with respect to the basic genetic algorithm,in optimal solution output rate.

Key words: genetic algorithm, robotic path planning, crossover operator, mutation operator, customized genetic operator

摘要: 提出了一种应用于机器人路径规划的改进型遗传算法。针对机器人路径规划的实际应用,优化设计了交叉算子和变异算子,引入了自定义的插入和删除两种遗传操作。通过把地图特征信息作为参与决策的已知条件来约束遗传算子的操作过程,提高了算法的进化效率。自定义遗传算子的使用,使得算法对复杂地图也表现出良好的适应能力。计算机仿真实验证明该算法在最优解输出概率方面相对于基本遗传算法有了显著提高。

关键词: 遗传算法, 机器人路径规划, 交叉算子, 变异算子, 自定义遗传算子