Intelligent Agent Supported Training in Virtual Simulations
Abstract
Simulation-based training in military decision making often requires ample personnel for playing various roles (e.g. team mates, adversaries). Usually humans are used to play these roles to ensure varied behavior required for the training of such tasks. However, there is growing conviction and evidence that intelligent agents can also produce human-like, variable behavior. At the same time, it is known that goal-directed, systematic training is more effective than learning-by-doing only. To achieve goal-directed, effective training in (embedded) virtual simulations, events in the simulated environment as well as the behavior of these intelligent agents must be carefully controlled. We propose to do that by using a director agent (DA). A DA can be seen as a supervisor, capable of diagnosing task performance, instructing intelligent agents and steering the simulation. These capacities enable a DA to control a training scenario not only on the basis of an off-line scenario model, but also on its on-line assessment of the trainee's task performance. A DA can thus bring about a simulation-based training tailored to the needs of the trainee, enhancing his or her learning experience. In this paper, we explain and illustrate the concept of a DA in the context of simulation-based training in on-board fire fighting.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 2009
- Accession Number
- ADA567749
Entities
People
- Annerieke Heuvelink
- Karel Van Den Bosch
- Maaike Harbers
- Willem A. Van Doesburg