Fighter flight trajectory prediction based on spatio-temporal graphcial attention network

TL;DR

This paper introduces a spatio-temporal graph attention network that combines Transformer and GAT to accurately predict fighter jet trajectories in high-speed air combat, enhancing prediction performance over existing methods.

Contribution

The paper proposes a novel ST-GAT model integrating Transformer and GAT for improved trajectory prediction in complex combat scenarios.

Findings

Significantly outperforms CNN-LSTM in prediction accuracy

Achieves 47% and 34% improvements in ADE and FDE metrics

Provides robust support for autonomous combat missions

Abstract

Quickly and accurately predicting the flight trajectory of a blue army fighter in close-range air combat helps a red army fighter gain a dominant situation, which is the winning factor in later air combat. However,due to the high speed and even hypersonic capabilities of advanced fighters, the diversity of tactical maneuvers,and the instantaneous nature of situational transitions,it is difficult to meet the requirements of practical combat applications in terms of prediction accuracy.To improve prediction accuracy,this paper proposes a spatio-temporal graph attention network (ST-GAT) using encoding and decoding structures to predict the flight trajectory. The encoder adopts a parallel structure of Transformer and GAT branches embedded with the multi-head self-attention mechanism in each front end. The Transformer branch network is used to extract the temporal characteristics of historical trajectories and capture the impact of the fighter's historical state on future trajectories, while the GAT branch network is used to extract spatial features in historical trajectories and capture potential spatial correlations between fighters.Then we concatenate the outputs of the two branches into a new feature vector and input it into a decoder composed of a fully connected network to predict the future position coordinates of the blue army fighter.The computer simulation results show that the proposed network significantly improves the prediction accuracy of flight trajectories compared to the enhanced CNN-LSTM network (ECNN-LSTM), with improvements of 47% and 34% in both ADE and FDE indicators,providing strong support for subsequent autonomous combat missions.