Unmanned Aerial Vehicle Tactical Intention Recognition Method Based on Dynamic Series Bayesian Network

To solve the problem of dynamic and sequential air combat intention recognition in complex battlefield environment, a target tactical intention recognition method based on the extended multi-entities Bayesian network (EMEBN) is proposed in this paper. First the dynamic series Bayesian network (DSBN) model is established to describe the process of intention representation and reasoning, the deficiency of the multi-entities Bayesian network (MEBN) in expressing the probability inference knowledge of the planning process is analyzed. Then the probability transfer MEBN fragments (PT-MFrags) and the series relation MEBN fragments (SR-MFrags) are introduced to depict the probability transfer and series relationship of rule knowledge. Finally, the feasibility and effectiveness of this method is verified by an experimental example.