An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban Areas
Inertial Navigation System (INS) is often combined with Global Navigation Satellite System (GNSS) to increase the positioning accuracy and continuity. In complex urban environments, GNSS/INS integrated systems suffer not only from dynamical model errors but also GNSS observation gross errors. Howeve...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/18/9/3091 |
id |
doaj-030bb2c13daa4169b37835dc34e69517 |
---|---|
record_format |
Article |
spelling |
doaj-030bb2c13daa4169b37835dc34e695172020-11-24T21:47:17ZengMDPI AGSensors1424-82202018-09-01189309110.3390/s18093091s18093091An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban AreasYipeng Ning0Jian Wang1Houzeng Han2Xinglong Tan3Tianjun Liu4NASG Key Laboratory for Land Environment and Disaster Monitoring, China University of Mining and Technology (CUMT), Xuzhou 221116, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Geodesy and Geomatics, Jiangsu Normal University, Xuzhou 221116, ChinaNASG Key Laboratory for Land Environment and Disaster Monitoring, China University of Mining and Technology (CUMT), Xuzhou 221116, ChinaInertial Navigation System (INS) is often combined with Global Navigation Satellite System (GNSS) to increase the positioning accuracy and continuity. In complex urban environments, GNSS/INS integrated systems suffer not only from dynamical model errors but also GNSS observation gross errors. However, it is hard to distinguish dynamical model errors from observation gross errors because the observation residuals are affected by both of them in a loosely-coupled integrated navigation system. In this research, an optimal Radial Basis Function (RBF) neural network-enhanced adaptive robust Kalman filter (KF) method is proposed to isolate and mitigate the influence of the two types of errors. In the proposed method, firstly a test statistic based on Mahalanobis distance is treated as judging index to achieve fault detection. Then, an optimal RBF neural network strategy is trained on-line by the optimality principle. The network’s output will bring benefits in recognizing the above two kinds of filtering fault and the system is able to choose a robust or adaptive Kalman filtering method autonomously. A field vehicle test in urban areas with a low-cost GNSS/INS integrated system indicates that two types of errors simulated in complex urban areas have been detected, distinguished and eliminated with the proposed scheme, success rate reached up to 92%. In particular, we also find that the novel neural network strategy can improve the overall position accuracy during GNSS signal short-term outages.http://www.mdpi.com/1424-8220/18/9/3091GNSS/INSdynamical model errorobservation gross errorfault detectionoptimal RBF neural networkadaptive robust filtering |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yipeng Ning Jian Wang Houzeng Han Xinglong Tan Tianjun Liu |
spellingShingle |
Yipeng Ning Jian Wang Houzeng Han Xinglong Tan Tianjun Liu An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban Areas Sensors GNSS/INS dynamical model error observation gross error fault detection optimal RBF neural network adaptive robust filtering |
author_facet |
Yipeng Ning Jian Wang Houzeng Han Xinglong Tan Tianjun Liu |
author_sort |
Yipeng Ning |
title |
An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban Areas |
title_short |
An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban Areas |
title_full |
An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban Areas |
title_fullStr |
An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban Areas |
title_full_unstemmed |
An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban Areas |
title_sort |
optimal radial basis function neural network enhanced adaptive robust kalman filter for gnss/ins integrated systems in complex urban areas |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2018-09-01 |
description |
Inertial Navigation System (INS) is often combined with Global Navigation Satellite System (GNSS) to increase the positioning accuracy and continuity. In complex urban environments, GNSS/INS integrated systems suffer not only from dynamical model errors but also GNSS observation gross errors. However, it is hard to distinguish dynamical model errors from observation gross errors because the observation residuals are affected by both of them in a loosely-coupled integrated navigation system. In this research, an optimal Radial Basis Function (RBF) neural network-enhanced adaptive robust Kalman filter (KF) method is proposed to isolate and mitigate the influence of the two types of errors. In the proposed method, firstly a test statistic based on Mahalanobis distance is treated as judging index to achieve fault detection. Then, an optimal RBF neural network strategy is trained on-line by the optimality principle. The network’s output will bring benefits in recognizing the above two kinds of filtering fault and the system is able to choose a robust or adaptive Kalman filtering method autonomously. A field vehicle test in urban areas with a low-cost GNSS/INS integrated system indicates that two types of errors simulated in complex urban areas have been detected, distinguished and eliminated with the proposed scheme, success rate reached up to 92%. In particular, we also find that the novel neural network strategy can improve the overall position accuracy during GNSS signal short-term outages. |
topic |
GNSS/INS dynamical model error observation gross error fault detection optimal RBF neural network adaptive robust filtering |
url |
http://www.mdpi.com/1424-8220/18/9/3091 |
work_keys_str_mv |
AT yipengning anoptimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT jianwang anoptimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT houzenghan anoptimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT xinglongtan anoptimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT tianjunliu anoptimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT yipengning optimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT jianwang optimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT houzenghan optimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT xinglongtan optimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas AT tianjunliu optimalradialbasisfunctionneuralnetworkenhancedadaptiverobustkalmanfilterforgnssinsintegratedsystemsincomplexurbanareas |
_version_ |
1725898067010387968 |