Predicting trajectory of drogue based on multi-head convolutional long-short-term memory network

Aerial refueling is an important technology of great military significance. It can effectively boost aircraft's performance owing to the longer period time and endurance range aircraft maintain in air. To solve problem that it hard for a receiver track drogue during its docking phase, trajectory prediction method based on multi-head convolutional long-short-term memory network proposed. First, one-dimensional sequence data extended high-dimensional space. Then spatial features are extracted through residual fused together. On this basis, adopted reveal underlying temporal correlations among predict drogue. The simulation experimental results show presented paper has higher accuracy than traditional methods use data.