Neural Network Assisted Vector Tracking Loop for Bridging GPS Signal Outages

Abstract

Signal blockage and reflections from buildings and other large, solid objects can lead to accuracy degradation. One of the merits of the Global Positioning System (GPS) vector tracking loop (VTL) architectures is that the tracking loop can be assisted in such degraded signal environments. This paper proposes the incorporation of the neural network (NN) into the VTL for improving the positioning quality. The NN is used to bridge the GPS signal and prevent the error growth due to signal outage from spreading into the entire tracking loop. The NNs are employed for predicting adequate numerical control oscillator (NCO) inputs, i.e., providing better prediction of residuals for the Doppler frequency and code phase in order to maintain regular operation of the navigation system. The NN-assisted VTL demonstrates the capability to ensure proper functioning of navigation system. Results show that the NN-assisted VTL can effectively provide improved performance during degraded signal environments such as GPS outages.