Real-time Decision Support in Online Training Environments
|Published in:||Proceedings of the 13th Latin American and Caribbean Conference for Engineering and Technology: Engineering Education Facing the Grand Challenges, What Are We Doing?|
|Date of Conference:||July 29 - 31, 2015|
|Location of Conference:||Santo Domingo, Dominican Republic|
|Multi-agency crisis management represents one of
the most complex real-world situations, requiring rapid
negotiation and decision-making under extreme pressure.
However, the training provided to Gold Commanders
(strategic planners), typically lacks the stress of a real crisis
and research tells us that behaviour and decision-making are
significantly affected by stress. It is therefore vital that
training puts trainees under the pressure of a real crisis
situation as far as is possible. The Pandora+ system has been
developed to provide a realistic, immersive, augmented reality
training environment in which the stress of each individual
trainee can be managed by the trainer, during a training event,
with the support of system intelligence. The system uses AI
planning techniques to manage an unfolding crisis scenario,
modelled as an event network which can be dynamically
updated by the trainer during a training event. This modelling
includes points of decision for trainees managed by automated
rules from a knowledge base, behavioural modelling of the
trainees, and ambient management of the environment to
provide affective inputs to control and manage trainee stress.
In this context, the system controls and reacts to trainee
performance in relation to the events and decision points and
can dynamically remodel and reconfigure the event network to
respond appropriately to trainee decisions. The environment
can also represent any missing trainees within the scenario and
has the potential to provide training in any domain where an
unfolding scenario of events are required for training.
Keywords— eLearning, Decision Support, Smart Environment, Crisis management training environment, timeline-based event network.