Adaptive Distributed Environment for Procedure Training (ADEPT)
- Created on Tuesday, 01 October 2013
ADEPT (Adaptive Distributed Environment for Procedure Training) is designed to provide more effective, flexible, and portable training for NASA systems controllers. When creating a training scenario, an exercise author can specify a representative rationale structure using the graphical user interface, annotating the results with instructional texts where needed. The author’s structure may distinguish between essential and optional parts of the rationale, and may also include “red herrings” — hypotheses that are essential to consider, until evidence and reasoning allow them to be ruled out.
The system is built from pre-existing components, including Stottler Henke’s SimVentive™ instructional simulation authoring tool and runtime. To that, a capability was added to author and exploit explicit control decision rationale representations. ADEPT uses SimVentive’s Scalable Vector Graphics (SVG)-based interactive graphic display capability as the basis of the tool for quickly noting aspects of decision rationale in graph form.
The ADEPT prototype is built in Java, and will run on any computer using Windows, MacOS, or Linux. No special peripheral equipment is required.
The software enables a style of student/ tutor interaction focused on the reasoning behind systems control behavior that better mimics proven Socratic human tutoring behaviors for highly cognitive skills. It supports fast, easy, and convenient authoring of such tutoring behaviors, allowing specification of detailed scenario-specific, but content-sensitive, high-quality tutor hints and feedback. The system places relatively light data-entry demands on the student to enable its rationale-centered discussions, and provides a support mechanism for fostering coherence in the student/tutor dialog by including focusing, sequencing, and utterance tuning mechanisms intended to better fit tutor hints and feedback into the ongoing context.
This work was done by Eric Domeshek, James Ong, and John Mohammed of Stottler Henke Associates, Inc. for Johnson Space Center. MSC-24493-1