HUMAN-COMPUTER COOPERATIVE PROBLEM-SOLVING - THEORY, DESIGN, AND EVALUATION OF AN INTELLIGENT ASSOCIATE SYSTEM

One approach to aiding the human supervisory controller of a complex d ynamic system is to provide an intelligent operator's associate. We pr opose a prescriptive theory of human-computer cooperative problem solv ing and describes the design and evaluation of a prototype system base d on the theory. The theory consists of five principles: human-in-char ge, mutual intelligibility, openness and honesty, management of troubl e, and multiple perspectives, A prototype intelligent associate system , the Georgia Tech Mission Operations Cooperative Assistant (GT-MOCA), is an embodiment of these principles that provides a collection of co ntext-sensitive resources for the human operator of a simulated satell ite ground control system. These resources include an interactive visu alization of current activities, an organized message lists of importa nt events, and interactive graphics depicting the current state of the controlled system, An evaluation study utilizing actual NASA satellit e ground controllers showed that GT-MOCA was perceived to be useful an d provided performance benefits for certain portions of the control ta sk.