COGENT

Abstract

In this paper, we demonstrate the feasibility of a cognitive agent, COGENT, to amplify human perceptual and cognitive abilities in complex high-value operational environments such as are found in spacecraft ground-based telemetry monitoring systems. The architecture of COGENT is based on Rasmussen's integrated theory of human information processing, and supports decisionmaking at multiple levels of abstraction and complexity. The decision-aiding process ranges from situation feature extraction and summarization to support perceptual processing, through situation assessment and alert generation to support enhanced situation awareness, to situation-specific response recommendation to support complex decision-making. COGENT displays information in a format that is easily understood, and matches the user's own mental model of the situation, thus requiring minimal amounts of translation and cognitive processing for assimilation. The robust performance of COGENT is assured through the use of complementary AI techniques such as probabilistic belief networks and argumentation. We developed and demonstrated a prototype for COGENT, and tested it on real telemetry data sets. We are specifically addressing our effort for enhancing operator situation awareness and decision-aiding capability at ground stations.