Neural network assisted ultra-tightly coupled GPS/INS integration for seamless navigation

Abstract

In GPS/INS integration, the ultra-tightly coupled approach involves the integration of I (in-phase) and Q (quadrature) components from the correlator of a GPS receiver with the INS data. The principal advantages of the Ultra Tightly Couple (UTC) structure is that a Doppler frequency derived from the INS is integrated with the tracking loops to improve the receiver tracking capability. The Doppler frequency shift is calculated and fed to the GPS tracking loops for elimination of the effect of stochastic errors caused by the Doppler frequency. The navigation information from INS can be converted into the Doppler information, which can be integrated with the GPS tracking loops to mitigate the Doppler on the GPS signal, resulting in the threshold improvement, thereby improving the overall system performance. An algorithm for bridging GPS outages using the radial basis function neural network (RBFNN) and Adaptive Network-Based Fuzzy Inference System (ANFIS) for providing better prediction of Doppler residual between GPS and prediction in order to maintain regular operation of the navigation system. The results demonstrate that the UTC with the assist of neural network can effectively improve the system robustness during GPS outages.