GMCL： a robust global localization method for mobile robot  

作　　者：罗荣华 Hong Bingrong Min Huaqing 

机构地区：[1]School of Computer Science and Engineering, South China University of Technology, Guangzhou 5106dO, P.R. China [2]School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, P.R. China

出　　处：《High Technology Letters》2006年第4期363-366,共4页高技术通讯（英文版）

摘　　要：A large sample size is required for Monte Carlo localization （MCL） in multi-robot dynamic environ- ment, because of the ＂kidnapped robot＂ phenomenon, which will locate most of the samples in the regions with small value of desired posterior density. For this problem the crossover and mutation operators in evolutionary computation are introduced into MCL to make samples move towards the regions where the desired posterior density is large, so that the sample set can represent the density better. The proposed method is termed genetic Monte Carlo localization （GMCL）. Application in robot soccer system shows that GMCL can considerably reduce the required number of samples, and is more precise and robust in dynamic environment.

关 键 词：global localization Monte Carlo localization evolutionary computation robot soccer 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]