PSO-LSSVR Assisted GPS/INS Positioning in Occlusion Region.

Li Xiaoming,Tan Xinglong,Zhao Changsheng

doi:10.3390/s19235256

Li Xiaoming, Tan Xinglong + Show 1 more

Open Access

https://doi.org/10.3390/s19235256

Copy DOI

Abstract

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.

Highlights

The multi-sensor integrated navigation system can obtain better positioning results when the observation environment is wide and the motion process is stable
A nonlinear Gauss process regression (GPR) based on the Particle swarm optimization (PSO) approach to perform vehicle position prediction during GPS outages was proposed which improved the position accuracy [13]
The accuracy of the differential GPS is 0.05 m, 0.05 m, 0.1 m in the three directions of the northeast, and the initial position error is set to 1 m, 1 m, 2 m, the initial attitude error set to 1◦, 1◦, 3◦

Summary

Introduction

The multi-sensor integrated navigation system can obtain better positioning results when the observation environment is wide and the motion process is stable. Satellite signals in forests, canyons, and tall buildings are subject to continuous or intermittent covered, multipath effects, and high-speed motion, causing the performance of integrated navigation systems to decline [1,2]. Guorong improved Sage adaptive filtering algorithm, which using UD (U is the unit upper triangular matrix, D is the diagonal matrix) decomposition to improves the adaptability of the system in high dynamic positioning [7]; Mohamed proposed moving window estimation and multi-model based adaptive estimation, which has a greater performance improvement than traditional filtering [8].

Objectives

Results

Conclusion