Skip navigation

Supporting real-time decision-making under stress in an online training environment

Supporting real-time decision-making under stress in an online training environment

Bacon, Liz, MacKinnon, Lachlan and Kananda, David (2017) Supporting real-time decision-making under stress in an online training environment. IEEE Revista Iberoamericana de Tecnologias del Aprendizaje. pp. 1-11. ISSN 1932-8540 (doi:https://doi.org/10.1109/RITA.2017.2659021)

[img]
Preview
PDF (Author Accepted Manuscript)
16434 BACON_Supporting_Real-time_Decision-Making_2017.pdf - Accepted Version

Download (579kB) | Preview
[img] PDF (Email of Acceptance)
16434 BACON_Acceptance_Email_2016.pdf - Additional Metadata
Restricted to Repository staff only

Download (188kB)

Abstract

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, while research tells us that behavior 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 possible. The Pandora+ system, developed from an EU FP7 research project, provides a unique, original, 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 model an unfolding crisis scenario, realized 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, behavioral modelling of the trainees, and dynamic 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 a timeline-based scenario of events is required for training. This entire approach is completely novel in crisis training and has been rigorously tested in several trials, the most recent involving close to 150 participants, and has the potential to transform online learning in many domains, not just crisis management.

Item Type: Article
Uncontrolled Keywords: eLearning; Decision Support; Smart Environment; Crisis management training environment; Timeline-based event network
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group: Greenwich Research into Innovative Pedagogies (GRIP)
Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Faculty of Engineering & Science
Last Modified: 04 Mar 2022 13:07
URI: http://gala.gre.ac.uk/id/eprint/16434

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics