Cognitive Agent Evaluation for Synthetic Pilot Training
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0201240" target="_blank" >RIV/00216305:26230/26:0201240 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/11257300/keywords#keywords" target="_blank" >https://ieeexplore.ieee.org/document/11257300/keywords#keywords</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/dasc66011.2025.11257300" target="_blank" >10.1109/dasc66011.2025.11257300</a>
Alternative languages
Result language
angličtina
Original language name
Cognitive Agent Evaluation for Synthetic Pilot Training
Original language description
The utilization of Computer Generated Forces (CGFs) represents a valuable tool in facilitating the training, analysis and development of emerging technologies, particularly within the context of a Beyond Visual Range (BVR) encounters. In this paper, a cognitive model of a tactical pilot, based on the principles of Situational Awareness (SA) and used to represent authentic air forces in tactical training, is subjected to a unique multi-stage validation procedure that allows defining its suitability as a substitute for a human pilot in simulated operational scenarios. The proposed validation focuses on the analysis of information comprehension using Working Memory (WM) models for measured and synthesized flight deck scan patterns, including the non-parametric Kolmogorov-Smirnov test, with the aim of investigating the similarity of the scan duration distribution across a pair of eye fixation samples. The WM analysis also addresses the cell activation process in light of the latest cognitive science metrics. Finally, a tactical simulation framework for an iterative evaluation of authentic agent behavior is presented, confirming the importance of using a cognitive agent model with natural behavioral variability to increase the realism of simulated missions.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20205 - Automation and control systems
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2025 AIAA DATC/IEEE 44th Digital Avionics Systems Conference (DASC)
ISBN
979-8-3315-2519-4
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
1-10
Publisher name
IEEE
Place of publication
Montreal, QC, Canada
Event location
Montreal
Event date
Sep 14, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001665766800122