A BiLSTM and CNN-Based Hybrid Algorithm for Extending Reliable Navigation Time During GNSS Spoofed

The errors of INS will accumulate rapidly and the navigation accuracy of integrated navigation system will decrease during GNSS is subjected to spoofing. To extend the reliable navigation time during GNSS spoofed, a hybrid optimization algorithm of CNN-BiLSTM is proposed in this paper. First, the sparrow search algorithm is used to optimize the network parameters to ensure that the network parameters can maximize the performance improvement under this problem. Then, the constructed network is trained by using the data when GNSS signals are available, and the mapping between the input features and GNSS position increment is established. The proposed hybrid optimization algorithm is verified by using the measured data set, and compared with LSTM algorithm. The results show that the proposed hybrid optimization algorithm can extend the reliable navigation time and improve the anti-spoofing performance of the navigation system when GNSS signals are spoofed and unavailable.