Flight Trajectory Prediction Method Based on Attentional Graph Convolutional Network

To address the problem of low trajectory prediction accuracy in aerial combat due to factors such as the high degree of freedom in fighter aircraft flight, diverse states, and uncertain air combat situations, a prediction algorithm based on an attention mechanism combined with a graph convolutional network encoder-decoder structure is proposed. First, the trajectory time domain features extracted by the long short-term memory network are input into the graph convolutional network to obtain its spatial domain features. Secondly, the attention mechanism is used to enhance the network's ability to learn the spatial antagonistic characteristics between fighter aircraft. Finally, the long short-term memory network outputs the predicted trajectory. Simulation experiments verify that compared with the original long short-term memory network trajectory prediction algorithm, this algorithm significantly reduces the average displacement error and final offset error in various environments.