Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning Approaches

Fighter pilots train maneuvers and missions in simulators with and against simulated entities that must exhibit realistic behavior for effective training. However, current simulated entities often display simplified behavior, and traditional methods for improving realism require extensive manual eff...

Full description

Saved in:
Bibliographic Details
Main Authors: Andreas Strand, Patrick Ribu Gorton, Karsten Brathen
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11037415/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849708686587461632
author Andreas Strand
Patrick Ribu Gorton
Karsten Brathen
author_facet Andreas Strand
Patrick Ribu Gorton
Karsten Brathen
author_sort Andreas Strand
collection DOAJ
description Fighter pilots train maneuvers and missions in simulators with and against simulated entities that must exhibit realistic behavior for effective training. However, current simulated entities often display simplified behavior, and traditional methods for improving realism require extensive manual effort to integrate domain knowledge. Recent advancements in machine learning, specifically reinforcement learning, imitation learning, and evolutionary algorithms, offer scalable alternatives by enabling agents to learn complex behavior from data. Despite improved methods, challenges remain in ensuring that agents reliably learn tactical maneuvers and proper employment of weapons and sensors in diverse scenarios. Another significant challenge is transferring agents from learning environments to military simulation systems because of differences in observation formats, action formats, and flight dynamic models. This survey categorizes the relevant literature in terms of applications, mission tasks, behavior model types, and machine learning methods, followed by a comparative analysis with an emphasis on the learning process. Based on this analysis, we present four primary recommendations: 1) standardization and research collaboration initiatives, 2) enhanced focus on multi-agent machine learning and cooperation, 3) utilization of hierarchical behavior models, and 4) emphasis on beyond-visual-range scenarios. These recommendations aim to address the current limitations and guide the development of more comprehensive, adaptable, and realistic machine learning-based behavior models for simulation-based pilot training.
format Article
id doaj-art-47122b2da3294ad89b6f7dc92ee24437
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-47122b2da3294ad89b6f7dc92ee244372025-08-20T03:15:35ZengIEEEIEEE Access2169-35362025-01-011311366611368510.1109/ACCESS.2025.358027911037415Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning ApproachesAndreas Strand0https://orcid.org/0000-0002-7679-7816Patrick Ribu Gorton1https://orcid.org/0000-0001-8588-1764Karsten Brathen2https://orcid.org/0000-0001-7347-8089Norwegian Defence Research Establishment (FFI), Kjeller, NorwayNorwegian Defence Research Establishment (FFI), Kjeller, NorwayNorwegian Defence Research Establishment (FFI), Kjeller, NorwayFighter pilots train maneuvers and missions in simulators with and against simulated entities that must exhibit realistic behavior for effective training. However, current simulated entities often display simplified behavior, and traditional methods for improving realism require extensive manual effort to integrate domain knowledge. Recent advancements in machine learning, specifically reinforcement learning, imitation learning, and evolutionary algorithms, offer scalable alternatives by enabling agents to learn complex behavior from data. Despite improved methods, challenges remain in ensuring that agents reliably learn tactical maneuvers and proper employment of weapons and sensors in diverse scenarios. Another significant challenge is transferring agents from learning environments to military simulation systems because of differences in observation formats, action formats, and flight dynamic models. This survey categorizes the relevant literature in terms of applications, mission tasks, behavior model types, and machine learning methods, followed by a comparative analysis with an emphasis on the learning process. Based on this analysis, we present four primary recommendations: 1) standardization and research collaboration initiatives, 2) enhanced focus on multi-agent machine learning and cooperation, 3) utilization of hierarchical behavior models, and 4) emphasis on beyond-visual-range scenarios. These recommendations aim to address the current limitations and guide the development of more comprehensive, adaptable, and realistic machine learning-based behavior models for simulation-based pilot training.https://ieeexplore.ieee.org/document/11037415/Air combatcomputer-generated forcesintelligent agentsmachine learningmodelingpilot training
spellingShingle Andreas Strand
Patrick Ribu Gorton
Karsten Brathen
Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning Approaches
IEEE Access
Air combat
computer-generated forces
intelligent agents
machine learning
modeling
pilot training
title Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning Approaches
title_full Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning Approaches
title_fullStr Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning Approaches
title_full_unstemmed Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning Approaches
title_short Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning Approaches
title_sort modeling air combat behavior for simulation based pilot training a survey of machine learning approaches
topic Air combat
computer-generated forces
intelligent agents
machine learning
modeling
pilot training
url https://ieeexplore.ieee.org/document/11037415/
work_keys_str_mv AT andreasstrand modelingaircombatbehaviorforsimulationbasedpilottrainingasurveyofmachinelearningapproaches
AT patrickribugorton modelingaircombatbehaviorforsimulationbasedpilottrainingasurveyofmachinelearningapproaches
AT karstenbrathen modelingaircombatbehaviorforsimulationbasedpilottrainingasurveyofmachinelearningapproaches