Intelligent Scenario Management Framework

Designing simulation-based training scenarios is becoming increasingly complex and instructor-intensive. This is particularly true with the additional goal to leverage the emerging large-scale distributed simulation environments with their inherent complexity. Currently, the technology used in simulation environments is antiquated and needs updating. Thus, in order to address the mixture of students (i.e., their backgrounds, aptitudes, mental models, capabilities, etc.), instructor doctrines, and training goals (e.g., accelerated learning, re-training, etc.) it has become necessary to define new methodologies in order to achieve effectiveness and uniformity in training content, student evaluation, and scenario generation. KBSI presents a new framework for generating simulation-based training scenarios. We integrate knowledge mined from historical databases (or trainee performance results) with that elicited from subject matter experts and then apply that integrated knowledge to facilitate the design or modification of training scenarios in order to generate scenarios automatically. We will also investigate the use of other data mining techniques such as Genetic Algorithms and Neural Networks. As a result we expect ISMF to: 1) assist the Common Instructor Operator Station subsystems by reducing the cognitive workload for instructors, 2) enable efficient scenario planning, 3) improve training effectiveness, and 4) result in improved student performance.