Rehearsing Naval Tactical Situations Using Simulated Teammates and an Automated Tutor

This paper describes a deployed simulation-based intelligent tutoring system (ITS) for training of tactical action officers (TAOs). The TAO on board a Navy ship is responsible for the operation of the entire watch team manning the ship´s command center. The ITS goal is to train the TAO in ldquocommand by negation,rdquo in which watchstanders perform their duties autonomously, while the TAO supervises, intervening in order to correct mistakes and rectify omissions. The ITS uses artificial intelligence (AI) techniques to provide Automated Role Players (ARPs) representing the watchstanders in the ship, and to provide a natural language interface to communicate with these automated teammates. An adaptive coaching strategy is used to provide coaching and feedback during an exercise. The paper presents a discussion of the ITS instructional design, its architecture, and the AI techniques it employs.