A hybrid fusion algorithm for GPS/INS integration during GPS outages

To enhance the performance of an integrated Global Positioning System and Inertial Navigation System (GPS/INS) during GPS outages, a novel hybrid fusion algorithm is proposed to provide a pseudo position information to assist the integrated navigation system. A new model that directly relates the velocity, angular rate and specific force of INS to the increments of the GPS position is established. Combined with a Kalman filter and an improved Multi-Layer Perceptron (MLP) network, the hybrid system is able to predict and estimate a pseudo GPS position when GPS signal is unavailable. Field test data are collected to experimentally evaluate the proposed model. The comparison results show: (1) the proposed model can effectively provide corrections to standalone INS during the 300s GPS outages, which also outperforms some of the widely used models; (2) our improved MLP method achieves better performance in the prediction of GPS position information than the normal artificial neural network (ANN) trained by Bayesian Regularization; (3) the best result can be reached when the current and past 1-step information of INS is utilized as the inputs of the artificial intelligence (AI) module.