MODEL-BASED COMMUNICATIVE ACTS - HUMAN-COMPUTER COLLABORATION IN SUPERVISORY CONTROL

Supervisory control environments can be characterized as dynamic, comp lex, uncertain, and risky. The cognitive demands placed on human super visory controllers are driven by the continual need for situation asse ssment (including active information seeking), active goal-setting and planning, and anticipatory as well as reactive control actions and co mpensating for abnormal system conditions. One way to improve the huma n-machine system is with intelligent support systems that provide cont ext-sensitive displays, dialogue, and resources for activity managemen t. The Georgia Tech Mission Operations Cooperative Assistant (GT-MOCA) is an example of such a system for NASA satellite ground control. The design of GT-MOCA is based on (1) principles of human-computer cooper ative problem solving, partly derived from an analysis of human commun ication literature, (2) empirical study of the use of an existing real -time expert system for satellite ground control, and (3) the OFMspert architecture which provides dynamic intent inferencing organized arou nd the operator function model. GT-MOCA provides three major resources for cooperative support: interactive graphics of system components, a n inspectable and interactive visualization of current activity requir ements, and message lists organized around major communicative functio ns such as advice and various types of alerts. This paper focuses on t he representation of the communicative acts that are the underpinning of these message lists and details how such acts are integrated into t he operator function model of activity. An analysis of GT-MOCA with re spect to human communication literature and an empirical evaluation of GT-MOCA show that it does support relevant and timely interaction wit h human problem solvers and does provide some performance benefits.