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

Abstract

Within training, scenario creation can be a long and costly activity. This often results in the same scenarios being re-used. While this can work with new trainees, it does not provide effective training for those using a system for continuing training. 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 are pursuing research investigating processes and tools for scenario generation, both manual and automated.A recently re-discovered approach (Shape Grammars) and a newly-developed approach (Functional L-systems) each shows great promise for their use in automated scenario generation. However, based on their additional expressive power, the authors have chosen to use Functional L-systems within their software, which will be reviewed.

A Review on Virtual Reality Skill Training Applications

“…They integrated the creation process of the virtual reality safety training system with a scenario-based design method to construct a general framework for creating VR training experiences. Martin et al (2009), Martin and Hughes (2010) developed software for automatic scenario generation, aiming at exploring the conceptual design of scenario generation approaches. Lin et al (2002) presented an architecture of VRbased training systems, as well as an introduction to virtual training task planning and some task-oriented training scenario models.…”

An interactive ontology-driven information system for simulating background radiation and generating scenarios for testing special nuclear materials detection algorithms

“…Scenarios are used in many areas to generate synthetic sequences of events including training/planning, resource allocation, estimating risks, evaluating physical models, etc. Martin and Hughes (2010) describe various approaches to implementing automated scenario generation including: 1) seeded approaches that blend human-created elements and system-automated processes; 2) heuristic approaches that create scenarios and their subcomponents by randomly selecting components and then comparing the scenario against the heuristics (Grois et al, 1998); 3) enumeration approaches which are a variant of the heuristic approaches in which all possible scenarios are enumerated; and 4) procedural modeling. The last approach was first popularized in computer graphics to create visual models, textures, and/or animations where rules and symbols were used to represent the elements being modeled.…”

“…The last approach was first popularized in computer graphics to create visual models, textures, and/or animations where rules and symbols were used to represent the elements being modeled. Examples of the procedural rules encoding are "shape grammars", L-systems (Lindenmayer systems) or Functional L-systems (Martin and Hughes, 2010).…”

“…After a careful review of previous efforts on automated scenario generation, Martin and Hughes (2010) note that "often scenario generation systems us a 'stovepipe' approach, which focuses only on a single simulation system." They propose that a better approach "would be to employ a robust data model that describes the rules and relationships required for each simulation component (Koziarz et al, 2003), allowing multiple simulation systems to be supported by a single scenario generation system and enabling the system itself to be extensible to multiple training domains."…”

Combinatorial Sequences for Disaster Scenario Generation

“…Some literature on the generation of scenarios for crisis exercises also exists; however, the scenarios devised therein are generally generated with a very specific and predetermined exercise goal in mind, simulating a disaster or crisis under very specific conditions, which are already well known and whose results can be anticipated and thus not really lead to new insights [4]. Additionally, a consequence of the highly time-consuming and expensive endeavor of developing scenarios for exercises is often that only a limited number of scenarios are being developed and constantly reused [5], which reduces the overall scope of the training and, subsequently, diminishes training effectiveness [6], especially in the case of continuous training [7]. Building upon [6], we argue that it is therefore crucial to the training effort to have the means to structurally derive "robust libraries" of diverse disaster scenarios which cover potential events, event combinations, and event sequences sufficiently well for some formal notion of coverage, which should be supported by "research-based heuristics to ensure that scenario outputs are domain-valid and pedagogically effective" [6].…”