Previous studies on the UAV swarm air combat decision-making problem lack consideration of uncertainty, intense confrontation, and high dynamics of aerial combat scenarios. This paper delves into the target allocation decision problem of the UAV attack and defense confrontation in a dynamic aerial combat environment. First, a dynamic game model is proposed to adapt changes in combat resources and adversaries’ behavior throughout multi-stage game processes. Then, the corresponding Nash equilibrium is solved based on a game learning algorithm- the Q-Learning algorithm. Finally, we consider the case where the UAV destructive probability is unknown, an uncertainty model is designed for predicting the UAV destructive probability based on the fuzzy comprehensive evaluation method.
Game Learning-Based Target Allocation of the UAV Confrontation System
Lect. Notes Electrical Eng.
International Conference on Guidance, Navigation and Control ; 2024 ; Changsha, China August 09, 2024 - August 11, 2024
2025-03-07
10 pages
Article/Chapter (Book)
Electronic Resource
English
Target-borne unmanned aerial vehicle for airspace confrontation
European Patent Office | 2022
|Study on Simulation Method of Radar Game Confrontation Process
British Library Conference Proceedings | 2022
|Study on Simulation Method of Radar Game Confrontation Process
Springer Verlag | 2022
|Reflections on the Confrontation Game Between UAV and Anti-UAV
British Library Conference Proceedings | 2022
|