Adaptive CGF for pilots training in air combat simulation

Training of combat fighter pilots is often conducted using either human opponents or non-adaptive computer-generated force (CGF) inserted with the doctrine for conducting air combat mission. The novelty and challenges of such non-adaptive doctrine-driven CGF is often lost quickly. Incorporating more...

Full description

Saved in:
Bibliographic Details
Main Authors: TENG, Teck-Hou, TAN, Ah-hwee, ONG, Wee-Sze, LEE, Kien-Lip
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2012
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6663
https://ink.library.smu.edu.sg/context/sis_research/article/7666/viewcontent/Adaptive_CGF_for_pilots_training_in_air_combat_simulation.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7666
record_format dspace
spelling sg-smu-ink.sis_research-76662022-01-13T09:35:19Z Adaptive CGF for pilots training in air combat simulation TENG, Teck-Hou TAN, Ah-hwee ONG, Wee-Sze LEE, Kien-Lip Training of combat fighter pilots is often conducted using either human opponents or non-adaptive computer-generated force (CGF) inserted with the doctrine for conducting air combat mission. The novelty and challenges of such non-adaptive doctrine-driven CGF is often lost quickly. Incorporating more complex knowledge manually is known to be tedious and time-consuming. Therefore, a study of using adaptive CGF to learn from the real-time interactions with human pilots to extend the existing doctrine is conducted in this work. The goal of this study is to show how an adaptive CGF can be more effective than a non-adaptive doctrine-driven CGF for simulator-based training of combat pilots. Driven by a family of self-organizing neural network, the adaptive CGF can be inserted with the same doctrine as the non-adaptive CGF. Using a commercial-grade training simulation platform, two human-in-the-loop (HIL) experiments are conducted using the adaptive CGF and the non-adaptive doctrine-driven CGF to engage two diverse groups of human pilots in 1-v-1 dogfights. The quantitative results and qualitative assessments of the CGFs by the human pilots are collected for all the training sessions. The qualitative assessments show the trainee pilots are able to match the adaptive CGF to the desirable attributes while the veteran pilots are only able to observe some learning from the adaptive CGF. The quantitative results show that the adaptive agent needs a lot more training sessions to learn the necessary knowledge to match up to the human pilots. 2012-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6663 https://ink.library.smu.edu.sg/context/sis_research/article/7666/viewcontent/Adaptive_CGF_for_pilots_training_in_air_combat_simulation.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
spellingShingle Databases and Information Systems
TENG, Teck-Hou
TAN, Ah-hwee
ONG, Wee-Sze
LEE, Kien-Lip
Adaptive CGF for pilots training in air combat simulation
description Training of combat fighter pilots is often conducted using either human opponents or non-adaptive computer-generated force (CGF) inserted with the doctrine for conducting air combat mission. The novelty and challenges of such non-adaptive doctrine-driven CGF is often lost quickly. Incorporating more complex knowledge manually is known to be tedious and time-consuming. Therefore, a study of using adaptive CGF to learn from the real-time interactions with human pilots to extend the existing doctrine is conducted in this work. The goal of this study is to show how an adaptive CGF can be more effective than a non-adaptive doctrine-driven CGF for simulator-based training of combat pilots. Driven by a family of self-organizing neural network, the adaptive CGF can be inserted with the same doctrine as the non-adaptive CGF. Using a commercial-grade training simulation platform, two human-in-the-loop (HIL) experiments are conducted using the adaptive CGF and the non-adaptive doctrine-driven CGF to engage two diverse groups of human pilots in 1-v-1 dogfights. The quantitative results and qualitative assessments of the CGFs by the human pilots are collected for all the training sessions. The qualitative assessments show the trainee pilots are able to match the adaptive CGF to the desirable attributes while the veteran pilots are only able to observe some learning from the adaptive CGF. The quantitative results show that the adaptive agent needs a lot more training sessions to learn the necessary knowledge to match up to the human pilots.
format text
author TENG, Teck-Hou
TAN, Ah-hwee
ONG, Wee-Sze
LEE, Kien-Lip
author_facet TENG, Teck-Hou
TAN, Ah-hwee
ONG, Wee-Sze
LEE, Kien-Lip
author_sort TENG, Teck-Hou
title Adaptive CGF for pilots training in air combat simulation
title_short Adaptive CGF for pilots training in air combat simulation
title_full Adaptive CGF for pilots training in air combat simulation
title_fullStr Adaptive CGF for pilots training in air combat simulation
title_full_unstemmed Adaptive CGF for pilots training in air combat simulation
title_sort adaptive cgf for pilots training in air combat simulation
publisher Institutional Knowledge at Singapore Management University
publishDate 2012
url https://ink.library.smu.edu.sg/sis_research/6663
https://ink.library.smu.edu.sg/context/sis_research/article/7666/viewcontent/Adaptive_CGF_for_pilots_training_in_air_combat_simulation.pdf
_version_ 1770576019505283072