关键词: 显式对手建模, 一对一超视距空战, 博弈, 策略模型, 决策点

Abstract: In order to explain and analyze the opponent’s air combat strategy, an Explicit Opponent Modeling (EOM) method for one-on-one Beyond Visual Range (BVR) air combat is proposed to address the lack of existing tools of strategy cogni-tion. The BVR problem is regarded as an imperfect information game, the space-time continuous process of BVR is discretized, different types of air combat actions are abstracted, the concept of decision point is introduced to aggre-gate the information sets conforming to the same distribution, the key decision variables are defined to examine the key factors affecting the actions, and the non-parametric machine learning approach is used to construct an easy-to-understand opponent strategy model (i.e., the model of the action probability distribution varies with the key decision variable in decision points). The post-game analysis of the simulated BVR air combat shows that the constructed strat-egy model by the proposed method can explain the opponent’s actions and analyze the opponent’s weak points more comprehensively than existing methods, and can provide suggestions for strategy optimization and equipment devel-opment.

Key words: Explicit opponent modeling, One-on-one Beyond Visual Range air combat, Game, Strategy model, Decision point