Modeling air combat situation assessment by using fuzzy dynamic Bayesian network

Automatic and accurate situation assessment is essential for unmanned combat air vehicles (UCAVs) to conduct and maintain their operations autonomously and effectively. The assessment forms the basis of threat assessment and plays an important role in implementing autonomous control and optimization for UCAVs. It is also a fundamental issue in developing combat decision-making support system for manned combat air vehicles (MCAVs). A novel approach was proposed as an attempt to tackle this challenging problem. A model based on discrete fuzzy dynamic Bayesian network was derived for UCAVs' situation assessment. A detailed theoretical analysis on the model and its inference method was given. Relevant simulation experiments were conducted and the results were discussed. It is shown that the presented model can predict accurately changes of the situation in a varying dynamical environment and has a good performance in terms of effective noise filtering from observations.