Knowledge-based reasoning in the Paladin tactical decision generation system

A real-time tactical decision generation system for air combat engagements, Paladin, has been developed. A pilot's job in air combat includes tasks that are largely symbolic. These symbolic tasks are generally performed through the application of experience and training (i.e., knowledge) gathered over years of flying a fighter aircraft. Two such tasks, situation assessment and throttle control, are identified and broken out in Paladin to be handled by specialized knowledge-based systems. Knowledge pertaining to these tasks is encoded into rule bases to provide the foundation for decisions. Paladin uses a customer-built inference engine and a partitioned rule-base structure to give these symbolic results in real time. An overview of knowledge-based reasoning systems as a subset of rule-based systems is provided. The knowledge used by Paladin in generating results as well as the system design for real-time execution is discussed. Paladin uses artificial intelligence techniques to address air-to-air combat and agile aircraft in a clear and concise manner. The Differential Maneuvering Simulator offers a unique opportunity to evaluate the performance of the Paladin software in a real-time tactical environment against human pilots.<
>