SVR Aided Adaptive Robust Filtering Algorithm for GPS/INS Integrated Navigation

Abstract

Abstract:

The number of observations is less than the number of state parameters in loosely-coupled global positioning system and inertial navigation system (GPS/INS) integrated navigation system. It is hard to distinguish dynamical model error from observation gross error using observation and state residuals, resulting from that the residuals are affected by both dynamical model error and observation gross error. A robust adaptive kalman filtering (RAKF) algorithm is put forward based on genetic algorithm and support vector regression (GA-SVR). The algorithm addresses the limits of anomaly detection on condition of lacking redundant observations. Support vector regression algorithm is used to train the mapping model for predicting suboptimal observations with parameter optimization based on genetic algorithm. The global abnormal detection, combined with the predicted observations, choose robust or adaptive kalman filtering autonomously for purpose of adjusting contribution of observations and dynamical model to the results. Finally field data on the vehicle are collected to verify the algorithm. It's shown that, dynamical model error can be distinguished from observation gross error based on GA-SVR, the influence of anomaly data is greatly weakened with RAKF algorithm to improve the reliability and accuracy of navigation solutions.

Key words: GPS/INS integrated navigation, anomaly detection, adaptive robust filtering, support vector regression

References

[1]YANG Yuan-xi, HE Hai-bo, XU Guo-chang.Adaptively Robust Filtering for Kinematic Geodetic Positioning[J].Journal of Geodesy, 2001, 75(2):109-116 [2]YANG Yuan-xi.Adaptive Kinematic Navigation and Positioning[M]. Beijing: Publishing House of Surveying and Mapping, 2006. (杨元喜.自适应动态导航定位[M].北京:测绘出版社, 2006.) [3]BRUMBACK B, SRINATH M.A Chi-square Test for Fault Detection in Kalman Filter[J].Automatic Control, IEEE Transactions on, 1987, 32(6):552-554 [4]DA R, LIN C F.Sensitivity Analysis Algorithm for the State Chi-square Test[J].Journal of guidance, control, and dynamics, 1996, 19(1):219-222 [5]CHEN J, PATTON R J.Robust Model Based Fault Diagnosis for Dynamic System[M]. Norwell: Kluwer Academic Publishers, 1999. [6]YANG Y X, GAO W G.A New L earning Statistic for Adaptive Filter Based on Predicted Residuals[J].Progress in Natural Science, 2006, 16(8):833-837 [7]YU Xue-xiang, LU Wei-cai.Robust Kalman Filtering Model and Its Application in GPS Monitoring Networks[J].ACTA GEODAETICA ET CARTOGRAPHIC SINICA, 2001, 30(1):27-31 [8]YANG Yuan-xi, ZHANG Shuang-cheng.Fittings of Systematic Errors and Covariance Matrices in Navigation[J].ACTA GEODAETICA ET CARTOGRAPHIC SINICA, 2004, 33(3):189-194 [9]LI Bofeng, SHEN Yunzhong.Equivalent Residual Product Based Outlier Detection for Variance and Covariance Component Estimation[J].ACTA GEODAETICA ET CARTOGRAPHIC SINICA, 2011, 40(1):10-14 [10]YANG Y X, GAO W G.An Optimal Adaptive Kalman Filter[J].Journal of Geodesy, 2006, 80(4):177-183 [11]WANG Jian, LIU Chao, GAO Jingxiang.GNSSINS Tightly Coupled Navigation based on Robust EKF Algorithm[J].Geomatics and Information Science of Wuhan University, 2011, 36(5):596-599 [12]MASSOUMNIA MA.A Geometric Approach t o the Synthesis of Failure Detection Filters[J][J].IEEE Trans on Automatic Control, 1986, 31(9):839-846 [13]WANG J J, WANG J, SINCLAIR D, et al.A Neural Network and Kalman Filter Hybrid Approach for GPS/INS Integration[C]//12th IAIN Congress & 2006 Int. Symp. on GPS/GNSS, Jeju, Korea. 2006: 18-20. [14]NOURELDIN A, OSMAN A, EL-SHEIMY N.A Neuro-Wavelet Method for Multi-Sensor System Integration for Vehicular Navigation[J].Measurement Science and Technology, 2004, 15(2):404-412 [15]SEMENIUK L, NOURELDIN A.Bridging GPS Outages using Neural Network Estimates of INS Position and Velocity Errors[J].Measurement Science and Technology, 2006, 17(9):2782-2798 [16]ABD-ELHAMID W, NOURELDIN A, EL-SHEIMY N.Adaptive Fuzzy Modeling of Low Cost Inertial Based Positioning Errors[J].IEEE Transactions on Fuzzy Systems, 2007, 15(3):519-529 [17]KAYGISIZ, BURAK H, ERKMEN, et al.Enhancing Positioning Accuracy of GPS/INS System during GPS Outages Utilizing Artificial Neural Network[J].Neural Processing Letters, 2007, 25(3):171-186 [18]GAO Wei-guang, YANG Yuan-xi.Neural Network Aided GPSINS Integrated Navigation Fault Detection Algorithms[J].ACTA GEODAETICA ET CARTOGRAPHIC SINICA, 2008, 37(4):403-409 [19]XU Z, LI Y, RIZOS C, et al.Novel Hybrid of LS-SVM and Kalman Filter for GPSINS Integration[J].Journal of Navigation, 2010, 63(2):289-298 [20]WANG Jianguo.Integration of GPS, INS and Pseudolite to Geo-Reference Surveying and Mapping Systemsp[D]. Sydney: University of Sydney, 2007. [21]LIU Guang jun, WU Xiao ping, GUO Jing.A Numerically Stable Sub-optimal Parallel Sage Adaptive Filter[J].ACTA GEODAETICA ET CARTOGRAPHIC SINICA, 2002, 31(4):283-288 [22]YANG Yuanxi, GAO Weiguang.A new learning statistic for adaptive filter based on predicted residuals[J].Progress in Natural Science, 2006, 16(8):833-837 [23]OU Jikun.Design of A New Scheme of Robust Estimation By Three Steps[J].ACTA GEODAETICA ET CARTOGRAPHIC SINICA, 1996, 25(3):173-179 [24]VAPNIK V.The Nature of Statistical Learning Theory[M]. springer, 2000. [25]STEINWART I, CHRISTMANN A.Support vector machines[M]. Springer, 2008. [26]B?CK T, SCHWEFEL H P.An overview of evolutionary algorithms for parameter optimization[J].Evolutionary computation, 1993, 1(1):1-23