Air Combat Intention Recognition with Incomplete Information Based on Decision Tree and GRU Network

Area of Science:

• Aerospace Engineering
• Artificial Intelligence
• Information Science

Background:

• Air combat information is often incomplete, uncertain, or deceptive.
• Accurate enemy intention recognition is critical for mission success.

Purpose of the Study:

• To develop a novel method for enemy intention recognition in uncertain air combat environments.
• To improve the accuracy and efficiency of predicting enemy fighter states and intentions.

Main Methods:

• Data repair using the highest frequency method (HFM) for missing state data.
• Gated recurrent unit (GRU) network for future state prediction.
• Intention decision tree with information entropy of partitioning (IEP) for rule extraction.
• Target maneuver tendency function to detect deceptive intentions.

Main Results:

• The proposed method demonstrates superior accuracy and efficiency in state prediction.
• Effective recognition of enemy fighter intentions, including deceptive maneuvers.
• Validation through one-to-one air combat simulations.

Conclusions:

• The novel intention recognition method is suitable for enemy fighter intention recognition in small air combat scenarios.
• The integration of GRU, HFM, and decision trees enhances situational awareness.
• The approach addresses the challenges of incomplete and uncertain battlefield information.