基于神经网络的FIRA仿真系统模糊策略的研究  

Fuzzy Strategy for Simulation System of FIRA Based on Neural Network

作　　者：黄进[1] 徐卫东[1] 卜怿鑫[1] 奚锦锦[1] 

机构地区：[1]中国矿业大学信息与电气工程学院,江苏徐州221000

出　　处：《计算技术与自动化》2009年第3期10-13,共4页Computing Technology and Automation

摘　　要：以FIRA足球仿真组作为平台,研究如何在具有动态性和不确定性的环境下足球比赛系统策略选择的问题。首先,分析出外部影响因子,选择神经网络系统作为策略选择的研究方向;在神经网络的基础上再加入模糊逻辑系统的研究,使它们集成在一个系统中,以发挥各自的优势,并与原来单一的神经网络进行比较,得出加入模糊策略的神经网络训练与学习效果更好。将该方法应用到2008年"百年矿大杯"第三届江苏省机器人比赛中获得了三等奖的好成绩,证明该方法确实有效。To FIRA soccer simulation team as a platform to examine how dynamic and uncertainty of the environment strategy football game system of choice. First of all, analyze the impact of external factors, neural network selection system as a strategy to select the direction of the research; neural network then add up the basic study of fuzzy logic system, so that they integrate in one system, in order to exert their own advantages, and with the original single comparison of neural networks, fuzzy strategy come to add neural network training and study better. The method is applied to the 2008 ＂The 100th anniversary of CUMT＂ the third robot, Jiangsu Province, won the third game in a good score to prove that the method is indeed effective.

关 键 词：影响因子 神经网络 模糊策略 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]