No abstract

No abstract

Under stress, human decision-makers revert to their best-practiced habits. This includes military commanders who may fail to act effectively under pressure for lack of sufficient practice. The US Army Research Institute (ARI) developed a training methodology emphasizing repeated exposure to small challenging vignettes enabling drill on command decision-making. Rather than role-play to a simulated conclusion, mentors focus on analyses and dialogues that explore reasoning and rationale. Adoption of this methodology in courses at Forts Leavenworth and Knox is helping to validate this approach to honing command skills. However, intense practice with human mentors is problematic as there are generally too few expert mentors available. This paper describes an ongoing Small Business Innovative Research (SBIR) project to develop automated intelligent tutors to fill the role of expert mentors. This project is developing a novel capability to understand, critique, and discuss proposed courses of action in a Socratic mode, guiding the student as an expert would. The approach emphasizes multi-modal interaction (e.g., language and graphics), models of expert human tutors, and development of authoring tools to reduce training system costs.The paper presents data from analyses of expert mentor and student dialogues during "tactical decision games." It then describes how this data is used to develop and assess the project's intelligent tutor. Additional preliminary data from early informal formative evaluation of the Phase I prototype system, and initial student feedback on some Phase II refinements is also reported.Ongoing complementary efforts include a related Phase II SBIR with a different ITS approach, and a computerbased program developed by ARI that human instructors are using in the Armor Captains Course at Fort Knox's University of Mounted Warfare. Author's BiographiesDr. Eric A. Domeshek is an Artificial Intelligence (AI) Project Manager at Stottler Henke Associates, Inc. He received his Ph.D. in Computer Science from Yale University, where his work focused on cognitive modeling and technology, most especially on development of Case Based Reasoning (CBR). While working as Research Faculty at the Georgia Institute of Technology, he helped launch the EduTech institute, and became involved in educational applications of AI and CBR. He continued to work on educational and training technology while on faculty at Northwestern University's Institute for the Learning Sciences. For the last three years, Dr. Domeshek has conceived and managed a variety of Intelligent Tutoring System (ITS) projects at Stottler Henke. His main effort currently focuses on dialogue-oriented tutors such as the ComMentor system described here. Mr. Elias Holman is an Report Documentation PageForm Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and revi...

This paper reports on a web-based groupware tool intended to support large distributed teams of engineers in modern engineering design practice. The Advanced Design Coordination Tool (ADCT) presents itself to members of a design team as a shared on-line set of engineers’ notebooks with flexible editing, filing, viewing, browsing, and searching capabilities. Additionally, its use of product, process, and decision representations referencing an explicit domain ontology, and tied together by dependency links, introduces artificial intelligence technology that enables capabilities beyond simple unstructured design history capture. The resulting repository can capture a rich and structured design rationale, which, with the system’s state management and versioning capability, enables recording active as well as rejected alternatives. The system currently exploits the captured data to improve team coordination: it applies dependency processing algorithms to automatically generate notifications to appropriate team members, based on changes to design notes or the detection of design conflicts. Over time, the accumulation of structured design histories with rationales should provide the basis for a knowledge repository that can proactively offer advice on new design challenges. This paper first sketches the context that makes this tool desirable, and then describes the system’s design and key capabilities. We finish with a discussion of limitations and future enhancements.

No abstract