非视距环境下基于PSO-SVM和RAIM的UWB定位方法  

UWB localization method based on PSO-SVM and RAIM in NLOS environment

作　　者：徐爱功[1] 王鹏语 隋心[1] 袁庆[2] 史政旭 王长强[1] XU Aigong;WANG Pengyu;SUI Xin;YUAN Qing;SHI Zhengxu;WANG Changqiang(School of Geomatics,Liaoning Technical University,Fuxin,Liaoning 123000,China;Engineering Survey Technology Application Research Institute,China Railway Siyuan Survey and Design Group Co.,Ltd.,Wuhan 430063,China)

机构地区：[1]辽宁工程技术大学测绘与地理科学学院,辽宁阜新123000 [2]中铁第四勘察设计院集团有限公司工程勘察研究院,武汉430063

出　　处：《测绘科学》2023年第4期1-9,45,共10页Science of Surveying and Mapping

基　　金：辽宁省重点研发计划项目(2020JH2/10100044);国家自然科学基金项目(42074012);辽宁省“兴辽英才计划”项目(XLYC2002101,XLYC2008034);辽宁省教育厅基础研究项目(LJ2020JCL016)。

摘　　要：针对室内定位过程中超宽带(UWB)信号容易受到非视距(NLOS)环境的影响从而降低定位的精度和稳定性的问题,该文提出了基于粒子群优化支持向量机(PSO-SVM)和自主完好性监测(RAIM)的误差识别算法,通过粒子群优化(PSO)算法对支持向量机(SVM)模型参数进行优化,将优化后的支持向量机模型用于UWB NLOS信号的识别,并利用自主完好性监测算法将异常的UWB测距值剔除。实验结果表明,该文算法能够对NLOS信号进行准确的识别,并有效提升了NLOS环境下UWB定位的精度及稳定性,平面定位误差可控制在0.26 m以内,东、北方向的均方根误差分别为0.09、0.11 m。Aiming at the problem that the ultra wide band(UWB) signal is easily affected by non line of sight(NLOS) environment during indoor positioning,which reduced the accuracy and stability of positioning,this paper proposed an error identification algorithm based on particle swarm optimization support vector machine(PSO-SVM) and receiver autonomous integrity monitoring(RAIM).The parameters of SVM model were optimized through the PSO algorithm.The optimized SVM model was used to identify the UWB NLOS signal,and RAIM was used to eliminate UWB outliers.The experimental results showed that the algorithm could accurately identify the NLOS signal,and effectively improved the accuracy and stability of UWB positioning in the NLOS environment.The planar positioning error could be controlled within 0.26 m,the root mean square errors in the east and north directions were 0.09 m and 0.11 m respectively.

关 键 词：室内定位 粒子群优化支持向量机 NLOS误差 自主完好性监测 异常测距值 

分 类 号：P228[天文地球—大地测量学与测量工程]