Automated Tutoring Dialogues for Training in Shipboard Damage Control
Abstract
This paper describes an application of state-of-the-art spoken language technology (OAA/Gemini/Nuance) to a new problem domain: engaging students in automated tutorial dialogs to evaluate and improve their performance in a training simulator. Shipboard damage control refers to the task of containing the effects of fire, explosions, hull breaches, flooding, and other critical events that can occur aboard Naval vessels. The high-stakes, high-stress nature of this task, together with limited opportunities for real-life training, make damage control an ideal target for artificial intelligence-enabled educational technologies like training simulators and tutoring systems. The simulator used in this study is DC-TRAIN, an immersive, multimedia training environment for damage control. DC-TRAIN's training scenarios simulate a mixture of physical phenomena (e.g., fire, flooding) and personnel issues (e.g., casualties, communications, standardized procedures). The current tutoring system is restricted to fire damage scenarios only, and in particular to the 12 fire scenarios available in DC-TRAIN version 2.5, but in future versions the authors plan to support post-session critiques for all of the damage phenomena that will be modeled by DC-TRAIN 4.0: fire, flooding, missile damage, and wall or firemain ruptures.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2001
- Accession Number
- ADA459671
Entities
People
- Brady Clark
- Heather Pon-barry
- J. Micah Fry
- Matt Ginzton
- Stanley Peters
Organizations
- Stanford University