Automatic Scenario Generation through Procedural Modeling for Scenario-Based Training

Abstract

We discuss our current efforts at developing automatic scenario generation software. We begin by explaining the rationale, and then review successful previous efforts. We discuss the lessons-learned from the past work, and the conceptual pieces that are required to generate operationally-valid scenarios that support effective training. We then present the conceptual design of our scenario generation approach, which uses novel procedural modeling approaches to ensure operational and training requirements are adequately met.Scenario-based training (SBT) is a highly-effective strategy for preparing individuals and teams for complex task domains. For maximum efficacy, SBT systems must include robust libraries of varied scenarios; however, the creation of validated, effective scenarios is time-consuming and must be carried out by highly-trained domain specialists, qualified instructors, and technology experts. The process is challenging and time-consuming, and therefore expensive. Thus, in practice, scenario libraries often fail to cover the optimal range of possible mission contexts. One way to facilitate the creation of more robust scenario libraries may be to automate the process of scenario generation. Automated scenario generation must be supported by appropriate algorithmic modeling approaches, as well as research-based heuristics to ensure that scenario outputs are domain-valid and pedagogically effective. In this paper, we explore both of these issues. From the perspective of computer science, we review procedural modeling techniques that can support automated scenario generation. From the perspective of training science, we discuss guidelines and research approaches for developing objective guidelines to ensure scenario effectiveness.

Scenario-Based Training: Scenario Complexity

“…While simulation-based training utilizes a type of virtual environment to enable practice of skills, a scenario can be thought of as the purposeful instantiation of simulator events to create the desired psychological states (Martin et al, 2009). Today, scenario-based training is widely accepted, and through it trainees learn to integrate multiple skills, cope with realistic distracters, practice higher order cognitive skills, and exercise naturalistic decision making (Cannon-Bowers & Salas, 1998).…”

Adaptive Instructor Operating Systems

“…It has been demonstrated as an effective method for training the integration of multiple complex skills, practicing higher order cognitive skills, and exercising naturalistic decision making Martin, Schatz, Bowers, Hughes, Fowlkes, & Nicholson, 2009). An advantage of scenario-based training lies in its ability to provide the context needed within the relevant dynamic and uncertain nature of the real world environment (Swezey & Salas, 1992).…”

A scenario generation framework for automating instructional support in scenario-based training

“…Unfortunately, this often results in only a small number of scenarios being developed and constantly reused. This not only reduces variety, but also may cause diminished training effectiveness (Martin et al, 2009). To help address these gaps, we are investigating processes and computational tools for automated scenario generation.…”

“…In order to provide an easier capability for instruction, the authors are pursuing a line of research in scenario generation. While this includes methods for instructors to build scenarios easily via a manual process, automated approaches for scenario generation are also being investigated.The authors have previously completed efforts in reviewing the needs of a scenario generation system (Martin et al, 2009) and in building a conceptual model for scenarios and how varying complexity can be achieved. This paper provides a review of this work and then presents a computational approach to automated scenario generation.…”

“…The authors have previously completed efforts in reviewing the needs of a scenario generation system (Martin et al, 2009) and in building a conceptual model for scenarios and how varying complexity can be achieved. This paper provides a review of this work and then presents a computational approach to automated scenario generation.…”