神经网络辅助的GPS/INS组合导航自适应UKF算法

doi:10.11947/j.AGCS.2015.20140216

测绘学报 ›› 2015, Vol. 44 ›› Issue (4): 384-391.doi: 10.11947/j.AGCS.2015.20140216

神经网络辅助的GPS/INS组合导航自适应UKF算法

谭兴龙^1,2, 王坚², 赵长胜¹

1. 江苏师范大学测绘学院, 江苏徐州 221116;
2. 中国矿业大学环境与测绘学院, 江苏徐州 221116

收稿日期:2014-04-24 修回日期:2014-08-29 出版日期:2015-04-20 发布日期:2015-04-27
作者简介:谭兴龙(1987—),男,讲师,博士,研究方向为GNSS/INS组合导航及数据处理.E-mail:tanxinglong3@126.com
基金资助:
国家自然科学基金(41174032);新世纪优秀人才支持计划(NCET-13-1019);江苏高校优势学科建设工程(SZBF2011-6-B35)

Neural Network Aided Adaptive UKF Algorithm for GPS/INS Integration Navigation

TAN Xinglong^1,2, WANG Jian², ZHAO Changsheng¹

1. School of Geodesy and Geomatics, Jiangsu Normal University, Xuzhou 221116, China;
2. Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China

Received:2014-04-24 Revised:2014-08-29 Online:2015-04-20 Published:2015-04-27
Supported by:
The National Natural Science Foundation of China(No.41174032);Program for New Century Excellent Talents in University (No. NCET-13-1019); Priority Academic Program Development of Jiangsu Higher Education Institutions (No. SZBF2011-6-B35)

摘要/Abstract

摘要： GPS/INS组合导航非线性系统最优估计算法中,基于统计信息和假设检验理论的多渐消因子自适应滤波算法的应用前提条件是残差向量为高斯白噪声.本文针对观测异常会影响残差向量的数字特性分布,提出了一种神经网络辅助的多重渐消因子自适应SVD-UKF算法.该算法采用神经网络算法削弱观测异常对残差序列高斯白噪声分布特性的影响,利用奇异值分解抑制UKF中先验协方差矩阵负定性变化,同时构造多重渐消因子对预测状态协方差阵进行调整,使得不同的滤波通道具有不同的调节能力,高效地应用于多变量复杂系统.最后利用车载实测数据进行了验证.结果表明,神经网络算法极大削弱了观测粗差对残差序列高斯白噪声分布特性的影响,拓展了多重渐消因子的应用范围,使其能在观测值含有粗差的条件下自适应调节不同滤波通道,消除滤波状态中的异常,提高组合导航解的精度和可靠性.

关键词: GPS/INS组合导航, 不敏卡尔曼滤波, 径向基神经网络, 多重渐消因子

Abstract: The predicted residual vectors should be zero-mean Gaussian white noise, which is the precondition for multiple fading factors adaptive filtering algorithm based on statistical information in GPS/INS integration system. However the abnormalities in observations will affect the distribution of the residual vectors. In this paper, a neural network aided adaptive unscented Kalman filter (UKF) algorithm with multiple fading factors based on singular value decomposition(SVD) is proposed. The algorithm uses the neural network algorithm to weaken the influence of the observed abnormalities on the residual vectors. Singular value decomposition instead of unscented transformation is adopted to suppress negative definite variation in priori covariance matrix of UKF. Since single fading factor in poor tracking of multiple variables has the limitation, multiple fading factors to adjust the predicted-state covariance matrix are constructed with better robustness so that each filter channel has different adjustability. Finally, vehicle measurement data are collected to validate the proposed algorithm. It shows that the neural network algorithm can prevent the observed abnormalities from affecting the distribution of the residual vectors, expanding the applied range of the adaptive algorithm. The neural network algorithm aided SVD-UKF algorithm with multiple fading factors is able to remove influences of state anomalies on condition of the observed abnormalities. The accuracy and reliability of the navigation solution can be improved by this algorithm.

Key words: GPS/INS integrated navigation, unscented Kalman filter, radial basis function neural network, multiple fading factors

中图分类号:

P228

谭兴龙, 王坚, 赵长胜. 神经网络辅助的GPS/INS组合导航自适应UKF算法[J]. 测绘学报, 2015, 44(4): 384-391.

TAN Xinglong, WANG Jian, ZHAO Changsheng. Neural Network Aided Adaptive UKF Algorithm for GPS/INS Integration Navigation[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(4): 384-391.

参考文献

[1] MOHAMED A H, SCHWARZ K P. Adaptive Kalman Filtering for INS/GPS[J]. Journal of Geodesy, 1999, 73(4): 193-203.
[2] YANG Y, HE H, XU G. Adaptively Robust Filtering for Kinematic Geodetic Positioning[J]. Journal of Geodesy, 2001, 75(2-3): 109-116.
[3] YANG Y, GAO W, ZHANG X. Robust Kalman Filtering with Constraints: A Case Study for Integrated Navigation[J]. Journal of Geodesy, 2010, 84(6): 373-381.
[4] 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. (李博峰, 沈云中. 基于等效残差积探测粗差的方差-协方差分量估计[J]. 测绘学报, 2011, 40(1): 10-14.)
[5] QIN Yongyuan, ZHANG Houyue, WANG Shuhua. Kalman Filter and Integrated Navigation Principle [M]. Xi'an: Northwest Industry University Press, 2012: 25-48. (秦永元, 张洪钺, 汪叔华.卡尔曼滤波与组合导航原理[M]. 西安: 西北工业大学出版社, 2012: 25-48.)
[6] DING W, WANG J, RIZOS C, et al. Improving Adaptive Kalman Estimation in GPS/INS Integration[J]. Journal of Navigation, 2007, 60(3): 517-529.
[7] SHI Xingxi, WANG Tiesheng, HUANG Bo. Integrated Localization Algorithm for DGPS/DR Based on SUT-EKF [J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(5): 528-533. (石杏喜, 王铁生, 黄波, 等. 基于SUT-EKF的 DGPS/DR 组合定位算法[J]. 测绘学报, 2010, 39(5): 528-533.)
[8] HIDE C, MOORE T, SMITH M. Adaptive Kalman Filtering for Low-cost INS/GPS[J]. Journal of Navigation, 2003, 56(1): 143-152.
[9] ARULAMPALAM M S, MASKELL S, GORDON N, et al. A Tutorial on Particle Filters for Online Nonlinear/non-Gaussian Bayesian Tracking[J]. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188.
[10] JULIER S J, UHLMANN J K. New Extension of the Kalman Filter to Nonlinear Systems[C]//Aero Sense'97. [S. l.]: International Society for Optics and Photonics, 1997: 182-193.
[11] JULIER S J, UHLMANN J K. Reduced Sigma Point Filters for the Propagation of Means and Covariances through Nonlinear Transformations[C]//Proceedings of the American Control Conference. Anchorage: IEEE, 2002: 887-892.
[12] YANG Y, GAO W. An Optimal Adaptive Kalman Filter[J]. Journal of Geodesy, 2006, 80(4): 177-183.
[13] GAO Weiguang, HE Haibo, CHEN Jinping. An Adaptive UKF Algorithm and Its Application for GPS/INS Integrated Navigation System[J]. Transactions of Beijing Institute of Technology, 2008, 28(6):505-509. (高为广, 何海波, 陈金平. 自适应UKF算法及其在GPS/INS组合导航中的应用[J].北京理工大学学报, 2008, 28(6): 505-509.)
[14] GAO Weiguang, YANG Yuanxi, ZHANG Ting. Neural Network Aided Adaptive Filtering for GPS/INS Integrated Navigation[J]. Acta Geodaetica et Cartographica Sinica, 2007, 36(1): 26-30. (高为广, 杨元喜, 张婷. 神经网络辅助的GPS/INS组合导航自适应滤波算法[J]. 测绘学报, 2007, 36(1): 26-30.)
[15] WU Fumei. Error Compensation and Extension of Adaptive Filtering Theory in GNSS/INS Integrated Navigation[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(3): 401-401. (吴富梅. GNSS/INS 组合导航误差补偿与自适应滤波理论的拓展[J]. 测绘学报, 2010, 40(3): 401-401.)
[16] TAN Xinglong, WANG Jian, HAN Houzeng. SVR Aided Adaptive Robust Filtering Algorithm for GPS/INS Integrated Navigation[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(6): 590-606. (谭兴龙, 王坚, 韩厚增. 支持向量回归辅助的 GPS/INS 组合导航抗差自适应算法[J]. 测绘学报, 2014, 43(6): 590-606.)
[17] ZHANG Chaowei, FU Li, FAN Yuezu. Multiple Fading Kalman Filter Based on Hypothesis Testing[J]. Journal of Beijing University of Aeronautics and Astronautics, 2004, 30(1): 18-22. (庄朝文, 富立, 范跃祖. 一种基于假设检验的多重渐消卡尔曼滤波[J]. 北京航空航天大学学报, 2004, 30(1): 18-22.)
[18] GENG Yanrui, GUO Wei, CUI Zhongxing. Comparative Research on Multiple Fading Kalman Filter in Integrated Navigation System[J]. Journal of Chinese Inertial Technology, 2004, 12(2): 18-22. (耿延睿, 郭伟, 崔中兴. 组合导航系统多重衰减因子自适应估计算法比较研究[J]. 中国惯性技术学报, 2004, 12(2):18-22.)
[19] CUI X, YANG Y. Adaptively Robust Filtering with Classified Adaptive Factors[J]. Progress in Natural Science, 2006, 16(8): 846-851.
[20] YANG Y, CUI X. Adaptively Robust Filter with Multi Adaptive Factors[J]. Survey Review, 2008, 40(309): 260-270.
[21] GAO W, MIAO L, NI M. Multiple Fading Factors Kalman Filter for SINS Static Alignment Application [J]. Chinese Journal of Aeronautics, 2011, 24:476-483.
[22] QIAN Minghua, GE Lei, PENG Yu. Multiple Fading Factors Kalman Filter and Its Application in SINS Initial Alignment[J]. Journal of Chinese Inertial Technology, 2012, 20(3): 287-291. (钱华明, 葛磊, 彭宇. 多渐消因子卡尔曼滤波及其在SINS初始对准中的应用[J]. 中国惯性技术学报, 2012, 20(3): 287-291.)
[23] KAYGISIZ B H, ERKMEN A M, ERKMEN I. Enhancing Positioning Accuracy of GPS/INS System during GPS Outages Utilizing Artificial Neural Network[J]. Neural Processing Letters, 2007, 25(3): 171-186.
[24] SESHAGIRI S, KHALIL H K. Output Feedback Control of Nonlinear Systems Using RBF Neural Networks[J]. IEEE Transactions on Neural Networks, 2000, 11(1): 69-79.
[25] XU Z, LI Y, RIZOS C, et al. Novel Hybrid of LS-SVM and Kalman Filter for GPS/INS Integration[J]. Journal of Navigation, 2010, 63(2): 289-299.

神经网络辅助的GPS/INS组合导航自适应UKF算法

Neural Network Aided Adaptive UKF Algorithm for GPS/INS Integration Navigation

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	谢先明. 结合滤波算法的不敏卡尔曼滤波器相位解缠方法[J]. 测绘学报, 2014, 43(7): 739-745.
[2]	谭兴龙王坚韩厚增. 支持向量回归辅助的GPS/INS组合导航抗差自适应算法[J]. 测绘学报, 2014, 43(6): 590-606.
[3]	柴艳菊,欧吉坤,袁运斌,阳仁贵,钟世明,王海涛. 附加方位约束的GPS/INS组合系统自适应选权滤波[J]. 测绘学报, 2011, 40(4): 0-441.
[4]	王家耀，谢明霞，郭建忠，陈科. 基于相似性保持和特征变换的高维数据聚类改进算法[J]. 测绘学报, 2011, 40(3): 269-275.