GA-SVR and Pseudo-position-aided GPS/INS Integration during GPS Outage
- 13 February 2015
- journal article
- research article
- Published by Cambridge University Press (CUP) in Journal of Navigation
- Vol. 68 (4), 678-696
- https://doi.org/10.1017/s037346331500003x
Abstract
The performance of Global Positioning System and Inertial Navigation System (GPS/INS) integrated navigation is reduced when GPS is blocked. This paper proposes an algorithm to overcome the condition where GPS is unavailable. Together with a parameter-optimised Genetic Algorithm (GA), a Support Vector Regression (SVR) algorithm is used to construct the mapping function between the specific force, angular rate increments of INS measurements and the increments of the GPS position. During GPS outages, the real-time pseudo-GPS position is predicted with the mapping function, and the corresponding covariance matrix is estimated by an improved adaptive filtering algorithm. A GPS/INS integration scheme is demonstrated where the vehicle travels along a straight line and around a curve, with respect to both low-speed-stable and high-speed-unstable navigation platforms. The results show that the proposed algorithm provides a better performance when GPS is unavailable.This publication has 26 references indexed in Scilit:
- An iterative LiDAR DEM-aided algorithm for GNSS positioning in obstructed/rapidly undulating environmentsAdvances in Space Research, 2013
- On-Line Smoothing for an Integrated Navigation System with Low-Cost MEMS Inertial SensorsSensors, 2012
- Performance Analysis of Constrained Loosely Coupled GPS/INS Integration SolutionsSensors, 2012
- Hybrid derivative-free extended Kalman filter for unknown lever arm estimation in tightly coupled DGPS/INS integrationGPS Solutions, 2010
- Novel Hybrid of LS-SVM and Kalman Filter for GPS/INS IntegrationJournal of Navigation, 2010
- Constructive neural-networks-based MEMS/GPS integration schemeIEEE Transactions on Aerospace and Electronic Systems, 2008
- INS/GPS Integration: Global Observability AnalysisIEEE Transactions on Vehicular Technology, 2008
- Adaptive Fuzzy Prediction of Low-Cost Inertial-Based Positioning ErrorsIEEE Transactions on Fuzzy Systems, 2007
- Improving Adaptive Kalman Estimation in GPS/INS IntegrationJournal of Navigation, 2007
- Multisensor integration using neuron computing for land-vehicle navigationGPS Solutions, 2003