【作者】 刘爽； 董洁； 李鹏威； 尹怡欣；

【Author】 LIU Shuang1,2,DONG Jie1,LI Peng-wei1,3,YIN Yi-xin1(1.School of Information Engineering,University of Science and Technology Beijing,Beijing 100083,China;2.Jilin Technology College of Electronic Information,Jilin 132023,China;3.School of Electrical and Information Engineering,Beihua University,Jilin 132023,China)

【机构】 北京科技大学信息工程学院；

【摘要】 当智能移动机器人在动态环境中进行目标形状识别时,融入了RS与BP网络结构的ANN相结合的智能控制算法。该算法利用RS的智能数据分析能力和BP网络的精准逼近能力,将两者的优点相结合。RS对训练样本集构成的信息表进行知识约简,发掘其中蕴含的最小决策规则,由规则构建ANN的网络拓扑结构,并进行最终决策识别。通过RS的约简,提高训练样本的有效率,并减小BP神经网络的规模。实验结果表明,加入智能算法后的机器人能够更加准确、快速地识别目标形状,满足了机器人识别目标的实时性的现实要求。更多还原

【Abstract】 When using mobile robot to recognize shape of object in dynamic surroundings,a hybrid recognition algorithm combines the rough set theory and BP neural network.RS has the capability for intelligent data analysis,and BP network can approach problems most accurately and exactly,the algorithm put respective advantages of two theories to use.Firstly,information table formed by training sample set was reduced by RS in order to find minimal decision regulations,and then the regulations confirmed the structure of ANN and recognized the shape of the object by BP neural network.At the same time,the reduction of RS enhanced the efficiency of training sample set,and simplified the scale of neural network.Experimental results show that the proposed algorithm has better performance in exactness and speed when compared with the only BP network.更多还原