Enhancing positioning accuracy of GPS/INS system during GPS outages utilizing artificial neural network

Kaygısız, Burak H.; Erkmen, Aydan M.; Erkmen, I.

doi:10.1007/s11063-007-9036-y

Cited by 20 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The single inertial navigation will make the position and attitude error of the carrier accumulate rapidly with time without be corrected. However, LSSVR can construct the mapping model by using the specific force increment

\int_{t_{k - 1}}^{t_{k}} f_{i b}^{b} d t

, the angular rate increment

\int_{t_{k - 1}}^{t_{k}} ω_{i b}^{b} d t

of the inertial component and GPS three dimensional position increment

P_{t_{k}}

when the integrated system is working normally [21,22,23], therfore PSO is used to search part of the global optimal parameters in the LSSVR algorithm. In the occlusion situation, the higher precision pseudo observations are predicted, and combine with the adaptive filtering to correct the INS error and estimate reliable navigation solution.…”

Section: Pso-lssvr Assisted Positioning In Occlusion Regionmentioning

confidence: 99%

PSO-LSSVR Assisted GPS/INS Positioning in Occlusion Region

Tan

Zhao

2019

Sensors

View full text Add to dashboard Cite

Satellite signals are easily lost in complex observation environments and high dynamic motion states, and the position and posture errors of pure inertial navigation quickly diverges with time. This paper therefore proposes a scheme of occlusion region navigation based on least squares support vector regression (LSSVR), and particle swarm optimization (PSO), used to seek the global optimal parameters. Firstly, the scheme uses the incremental output of GPS (Global Positioning System) and Inertial Navigation System (INS) when the observation is normal as the training output and the training input sample, and then uses PSO to optimize the regression parameters of LSSVR. When the satellite signal is unavailable, the trained mapping model is used to predict the GPS pseudo position. Secondly, the observed anomaly is detected by the test statistic in the integrated navigation solution filtering estimation, and the exponential fading adaptive factor is introduced to suppress the influence of the abnormal pseudo observation value. The results indicate that the algorithm can predict the higher precision GPS position increment, and can effectively judge some abnormal observations that may occur in the predicted value, and adjust the observed noise covariance to suppress the anomaly observation, which can effectively improve the continuity and reliability of the integrated navigation system in the occlusion region.

show abstract

\int_{t_{k - 1}}^{t_{k}} f_{i b}^{b} d t

, the angular rate increment

\int_{t_{k - 1}}^{t_{k}} ω_{i b}^{b} d t

of the inertial component and GPS three dimensional position increment

P_{t_{k}}

Section: Pso-lssvr Assisted Positioning In Occlusion Regionmentioning

confidence: 99%

PSO-LSSVR Assisted GPS/INS Positioning in Occlusion Region

Tan

Zhao

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Modern literature sometimes proposes that the integrated satellite/Low-Cost IMU system based on the Kalman filtering for some applications could be replaced or aided by the other mathematical solutions such as the Multi-layer Feed-forward Neural Networks (MFNN), the Constructive Neural Network (CNN) (Huang and Chiang, 2008), the Artificial Neural Network (Kaygýsýz et al, 2007), and the Fussy Modelling (Abdel-Hamid et al, 2006, p. 3). Nevertheless, Wagner and Wieneke (2003, p. 544) point out that the conventional methods based on Kalman filtering and similar to the one shown in Table 2 are widely accepted.…”

Section: Below and In Imu (50 Hz) And [D]gpsmentioning

confidence: 99%

Analysis of some low- and high-dynamics errors of Low-Cost IMU

Vorbrich¹

2011

Geodesy and Cartography

View full text Add to dashboard Cite

Abstract:The paper expounds relevant results of some of the present author's experiments defining the strapdown IMU sensors' errors and their propagation into and within DGPS/IMU. In order to deal with this problem, the author conducted both the laboratory and field-based experiments.In the landborne laboratory the stand-alone Low-Cost IMU MotionPak MKII was verified in terms of the accelerometer bias, scale factor, gyroscope rotation parameters and internal temperature cross-correlations.The waterborne field-trials based on board dedicated research ships at the lake and at the busy small sea harbour were augmented by the landborne ones. These experiments conducted during the small, average, and high dynamics of movement provided comparative sole-GPS, stand-alone DGPS and integrated DGPS/IMU solution error analysis in terms of the accuracy and the smoothness of the solution. This error estimation was also carried on in the context of the purposely-erroneous incipient DGPS/IMU initialisation and alignment and further in the circumstances of on-flight alignment improvement in the absence of the signal outages.Moreover, the lake-waterborne tests conducted during extremely low dynamics of movement informed about the deterioration of the correctly initialised DGPS/IMU solution with reference to the stand-alone DGPS solution and sole-GPS solution.The above-mentioned field experiments have checked positively the DGPS/MKI research integrating software prepared during the Polish/German

show abstract

“…For example, one such ANN architecture is the feed-forward neural network (FFNN). More specifically, the FFNN architecture is currently being considered as the state-of-the-art method to bridge GPS outages in time-domain solutions (see Chiang et al (2003); Kaygisiz et al (2004) ; Jwo and Huang, (2004); Chiang et al (2006); Wang et al, 2006; Kaygisiz et al (2007) ). The FFNN is an interconnection of layers (vectors) in which data and calculations flow in a single direction, from the input layer (vector) to hidden layer(s) (vector(s)) and then the output layer (vector).…”

Section: Current State-of-the-art Bridging Models For Gps Outagesmentioning

confidence: 99%

A Frequency-Domain INS/GPS Dynamic Response Method for Bridging GPS Outages

El-Diasty

Pagiatakis

2010

J. Navigation

View full text Add to dashboard Cite

We develop a new frequency-domain dynamic response method to model integrated Inertial Navigation System (INS) and Global Positioning System (GPS) architectures and provide an accurate impulse-response-based INS-only navigation solution when GPS signals are denied (GPS outages). The input to such a dynamic system is the INS-only solution and the output is the INS/GPS integration solution ; both are used to derive the transfer function of the dynamic system using Least Squares Frequency Transform (LSFT). The discrete Inverse Least Squares Frequency Transform (ILSFT) of the transfer function is applied to estimate the impulse response of the INS/GPS system in the time domain. It is shown that the longterm motion dynamics of a DQI-100 IMU/Trimble BD950 integrated system are recovered by 72%, 42%, 75%, and 40% for north and east velocities, and north and east positions respectively, when compared with the INS-only solution (prediction mode of the INS/GPS filter). A comparison between our impulse response model and the current state-of-the-art time-domain feed-forward neural network shows that the proposed frequency-dependent INS/GPS response model is superior to the neural network model by about 26% for 2D velocities and positions during GPS outages. K E Y

show abstract

Enhancing positioning accuracy of GPS/INS system during GPS outages utilizing artificial neural network

Cited by 20 publications

References 5 publications

PSO-LSSVR Assisted GPS/INS Positioning in Occlusion Region

PSO-LSSVR Assisted GPS/INS Positioning in Occlusion Region

Analysis of some low- and high-dynamics errors of Low-Cost IMU

A Frequency-Domain INS/GPS Dynamic Response Method for Bridging GPS Outages

Contact Info

Product

Resources

About