GPS/BDS VTL-assisted by the NN for complex environments
In complex landform the satellite signals are blocked so seriously that BeiDou satellite navigation system (BDS) cannot achieve real-time high-precision dynamical positioning, which seriously restrict its widespread in precise mapping and disaster relief. This study proposes global positioning system (GPS)/BDS vector tracking loop (VTL) assisted by the neural network (NN) to improve the performance of receivers in complex environments. In GPS/BDS VTL, pre-filter and navigation extended Kalman filter are both used, and discriminators are replaced by pre-filter structure; then, the output information of pre-filter is used as input of the navigation filter, at the same time the pseudorange rate of pre-filter is updated by pseudorange rate of navigation filter; finally, the NN is used in the GPS/BDS vector tracking structure, in the training stage, the output from navigation filter is adopted as the input of the NN. This method can prevent the error growth due to weak signal from deteriorating the entire tracking loop performance. Moreover, the NN is employed to provide a better prediction of residuals such as the Doppler frequency and code phase. The results show that the proposed adaptive GPS/BDS VTL shows a better tracking performance compared with the conventional VTL.