Representing Entity Actions and Cue Taxonomies (REACT)

Effective evaluation of human-machine systems requires accurate representations of human behavior. Human response to suppression is particularly important because it typically interrupts a mission task which, if continued or completed, would impact the outcome of the engagement. Currently, simulations only take into account a fraction of the perceptual cues to which humans respond under suppressive fire, and a small number of behavioral responses. This is due in part to a lack of empirical data, and to limited knowledge of physical and cognitive factors that constrain responses to suppressive fire. We propose to address the need for realistic, flexible, easy-to-update models by designing and prototyping a framework for Representing Entity Actions and Cue Taxonomies (REACT). Our human centric approach uses Cognitive Systems Engineering techniques to support the necessary knowledge elicitation and analysis efforts. This process will identify and categorize suppression cues, associate them with behaviors, and identify REACT software system requirements. We will then develop and implement methods to populate areas lacking in data to provide an enhanced representation of the role of suppression in decision making and performance. Finally, we will integrate the REACT framework into the Infantry Warrior Systems (IWARS).