基于单亲遗传算法的RoboCup动态角色分配  

Algorithm on Role Dynamic Allocating of RoboCup Based on Partheno-genetic Algorithm

作　　者：李亘[1] 王国伟[1] 黄苗[1] 邓本再[1] 李茂军[1] 

机构地区：[1]长沙理工大学电气与信息工程学院,湖南长沙410114

出　　处：《计算技术与自动化》2010年第1期55-57,83,共4页Computing Technology and Automation

摘　　要：RoboCup的机器人动态角色分配问题是一个典型的组合优化问题。解决这一问题的传统方法是贪心法,但贪心法易陷入局部最优解。提出用针对组合优化问题而构造的序号编码单亲遗传算法解决RoboCup的机器人动态角色分配问题。单亲遗传算法借鉴了传统遗传算法"优胜劣汰"的自然选择机制,但只通过单个体繁殖后代,在解决组合优化问题和复杂工程优化问题方面具有明显的优越性。试验结果显示这种方法的在解决RoboCup机器人动态角色分配问题时的有效性。Role dynamic allocating problem of robot in RoboCup is a typical combinatorial optimization problem, The tra- ditional method to solve this problem is the greedy algorithm that the solution is easily into suboptimization in the calcula- tion. In this paper, role dynamic allocating problem of robot in RoboCup is solved by partheno--genetic algorithm which is using ordinal character strings as chromosome for solving combinatorial optimization problems. Partheno--genetic algorithm which is from the ＂survival of the fittest＂ mechanism of natural selection of traditional genetic algorithm and propagating by Single individual has obvious advantages in solving combinatorial optimization problems and complex engineering optimization problems. Experiments results showed that the Partheno--Genetic Algorithm is effective in solving the Role dynamic alloca- ting problem of robot in RoboCup.

关 键 词：ROBOCUP 机器人 动态角色分配 单亲遗传算法 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]