ACLSTM integrated navigation method based on multimodal fusion under GPS interruption

In order to improve the defect of the traditional filtering method in the scenario of GPS signal interruption to suppress the nonlinear error, this paper proposes a convolutional long short-term memory neural network based on attention mechanism under multimodal fusion (MF-ACLSTM). In this model, spatial feature extraction is carried out by convolutional neural networks (CNN), and temporal feature modeling is carried out by combining long short-term memory neural networks (LSTM) to effectively integrate inertial navigation and GPS data, and attention mechanism is introduced to dynamically adjust the contribution weights of different sensor modalities to navigation estimation. When the GPS signal is interrupted, the autoregressive mechanism of historical inertial navigation data and model is used to achieve short-term accurate prediction and long-term error suppression, so as to make the navigation results more accurate. Experimental results show that the proposed method has a significant improvement in positioning error and long-term stability compared with the traditional filtering method in the GPS signal interruption scenario.