A knowledge-based decision aid for enhanced situational awareness

This paper describes a multi-year research and development effort to develop a system for performing situation assessment in next-generation Army helicopters. We first provide a formal definition of situation assessment and describe the motivation for the architecture based on studies in human cognition and attention. The paper describes the overall architecture and the processing paradigm used in performing situation assessment. In particular, we show how extensive knowledge about the battlefield, the threat, terrain, enemy and friendly doctrine can be used to aid in performing situation assessment. We also show how the overall inferencing process can be controlled in such a way as to bound the requirements for scarce computational resources. We describe a system composed of three independent reasoning subsystems performing recognition, evaluation and prediction. We also describe the knowledge bases and important data structures used in developing the system