Cognitive man-machine-cooperation: modeling operators' general objectives and its role within a cockpit assistant system

Abstract

Modern cockpit environments, covering highly integrated and complex automatic functions, pose various demands on the crew. Aircraft manufacturers and flying organizations try to alleviate crew decision-making as much as possible. This is done by means of automation and by establishing standard procedures and checklists to cover anticipated failures or emergencies. So far, automation often leads to clumsiness, which is considered to be a major reason for severe deficiencies concerning the interaction between cockpit crew and aircraft systems. Cognitive systems appear to be a promising approach to overcome these deficiencies in future cockpits. They cover the capabilities for situation interpretation, planning and decision making as well as autonomous execution of a plan. Cognitive assistant systems are designed to make use of these capabilities in favor of a cooperative approach. The cognitive process and its cognitive components are introduced. The cooperation between man and cognitive assistant system poses new demands. An explicit 'mental model' is a fundamental requirement for the assistant system. Analysis, behavior, design and the role of explicit 'mental models' within a cognitive cockpit assistant system are described. Methods for knowledge acquisition and representation are discussed with respect to a model of general objectives, which the crew of a military transport aircraft has in mind. The implementation using a CORBA environment and the validation by in-flight data of the Crew Assistant Military Aircraft CAMA are briefly described.