High-precision filtering estimation is one of the key techniques for strapdown inertial navigation system/global na-vigation satellite system(SINS/GNSS)integrated navigation sys-tem,and its estimation plays an important role in the perfor-mance evaluation of the navigation system.Traditional filter esti-mation methods usually assume that the measurement noise conforms to the Gaussian distribution,without considering the influence of the pollution introduced by the GNSS signal,which is susceptible to external interference.To address this problem,a high-precision filter estimation method using Gaussian pro-cess regression(GPR)is proposed to enhance the prediction and estimation capability of the unscented quaternion estimator(USQUE)to improve the navigation accuracy.Based on the advantage of the GPR machine learning function,the estimation performance of the sliding window for model training is mea-sured.This method estimates the output of the observation information source through the measurement window and rea-lizes the robust measurement update of the filter.The combina-tion of GPR and the USQUE algorithm establishes a robust mechanism framework,which enhances the robustness and sta-bility of traditional methods.The results of the trajectory simula-tion experiment and SINS/GNSS car-mounted tests indicate that the strategy has strong robustness and high estimation accu-racy,which demonstrates the effectiveness of the proposed method.

LYU Xu;HU Baiqing;DAI Yongbin;SUN Mingfang;LIU Yi;GAO Duanyang

College of Electrical Engineering,Naval University of Engineering,Wuhan 430033,China;Beijing Huahang Radio Measurement Research Institute,Beijing 100000,China;School of Electrical Engineering,Liaoning University of Technology,Jinzhou 121001,China;School of Electronics and Information Engineering,Harbin Institute of Technology,Harbin 150001,China

系统工程与电子技术（英文版）

[1]LYU Xu;HU Baiqing;DAI Yongbin;SUN Mingfang;LIU Yi;GAO Duanyang-.Gaussian process regression-based quaternion unscented Kalman robust filter for integrated SINS/GNSS)[J].系统工程与电子技术（英文版）,2022(05):1079-1088

vigation,USQUE,lizes

Gaussian,process,regression,quaternion,unscented,Kalman,integrated,SINS,GNSS,High,precision,filtering,estimation,one,key,techniques,strapdown,inertial,navigation,system,global,satellite,its,plays,important,role,evaluation,Traditional,methods,usually,assume,that,measurement,noise,conforms,distribution,without,considering,influence,pollution,introduced,by,signal,which,susceptible,external,interference,To,address,this,problem,high,using,GPR,proposed,prediction,capability,estimator,improve,accuracy,Based,advantage,machine,learning,function,performance,sliding,window,model,training,sured,This,estimates,output,observation,information,source,through,rea,update,combina,algorithm,establishes,mechanism,framework,enhances,robustness,traditional,results,trajectory,simula,experiment,car,mounted,tests,indicate,strategy,has,strong,demonstrates,effectiveness

0.498117