PROJECT TITLE: COGENT: Cognitive Agent to Amplify Human Perception and Cognition
TECHNICAL ABSTRACT (LIMIT 200 WORDS)
We propose to develop a cognitive agent, COGENT, to amplify human perceptual and cognitive abilities in complex high-value operational environments such as manned space systems. The robust and adaptive architecture we propose for COGENT is based on Rasmussen's integrated theory of human information processing, and will support decision-making at multiple-levels of abstraction and complexity. The decision-aiding process ranges from simple perceptual enhancement of situation features 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. Derived decision aids can then be presented in a format that is easily understood and that matches the user's own mental model of the situation, thus requiring minimal amounts of translation and cognitive processing for assimilation. Robust performance is assured through the use of complementary AI techniques such as fuzzy logic, probabilistic belief nets, and rule-based argumentation. Adaptive assistance is provided by learning patterns in past operational data which predict significant events, and also by learning preferred user task and display profiles. We propose to develop COGENT using COTS software, demonstrate its use onboard for anomaly detection using spacecraft telemetry data, and illustrate how it supports alert generation and decision-aiding.
POTENTIAL COMMERCIAL APPLICATIONS
Commercial applications of the generic COGENT architecture and methodology exist for a wide variety of contexts characterized by high-information flow rates, decision-making under uncertainty, and distributed "players." Such application areas include operation centers for complex process control (e.g., nuclear power plants), financial services, and rail and air traffic management centers. Vertical applications for these markets would significantly enhance decision-aiding and improve effectiveness and safety in a number of life-critical applications.
NAME AND ADDRESS OF PRINCIPAL INVESTIGATOR
Subrata K. Das
Charles River Analytics Inc.
One Alewife Center
Cambridge , MA 02140
NAME AND ADDRESS OF OFFEROR
Charles River Analytics Inc.
One Alewife Center
Cambridge , MA 02140