This paper studies the problem of UAV collaborative decision-making in intelligent aerial game. In view of the complexity of the aerial game, including uncertainty, information incompleteness and dynamics, a strong robust UAV collaborative decision-making technology is proposed, which aims to improve the combat effectiveness of a UAV in complex confrontation environments. Based on a simulation platform with a high degree of simulation, the situational awareness and information fusion technology are used to establish an air combat situation analysis model by constructing a threat index and a comprehensive advantage index, and the design of C4.5 rule tree algorithm is improved, and three decision-making models are established: the upper level determines the decision, the middle layer determines the task, and the lower level determines the behavior, so as to optimize the tactical behavior and response speed of the UAV. Through experimental verification, it is found that the technology significantly improves the accuracy and execution efficiency of UAV decision-making, thereby improving its combat effectiveness in complex air combat environments. The research results can provide a theoretical basis and technical support for the design and implementation of multi-UAV cooperative combat systems in the future.