Exploring Hierarchical Hybrid Autonomous Maneuvering Decision-Making Architecture in Beyond Visual Range Air Combat

The research on beyond visual range air combat presents several notable challenges, including numerous elements, nonlinear coupling of dynamic models, and complex changes in the dynamics of the game. Directly applying traditional algorithms to address these challenges can result in an extensive solution space, making it difficult to elucidate the dynamic process of air combat confrontation. One-versus-one (1V1) beyond visual range air combat, as the foundational level of air combat research, holds significant importance for analyzing and understanding the game confrontation process in air combat scenarios. To address these challenges, this paper focuses on 1V1 two-plane beyond visual range air combat, analyzing the air combat process and constructing an air combat decision-making model. Building upon a typical hierarchical hybrid decision-making architecture for beyond visual range air combat, the paper develops a decision-making method based on rule-driven state transition behavior in air combat games. Additionally, the evolution of the two-plane confrontation game is analyzed and studied using evolutionary game theory. Simulation results demonstrate that the proposed decision-making method exhibits strong autonomous decision-making capabilities and provides a competitive edge in two-plane beyond visual range air combat scenarios. Furthermore, it offers good interpretability and logical coherence.