Engagement Decision Support for Beyond Visual Range Air Combat

Dantas, Joao P. A.; Costa, Andre N.; Geraldo, Diego; Máximo, Marcos R. O. A.; Yoneyama, Takashi

doi:10.1109/lars/sbr/wre54079.2021.9605380

Cited by 11 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments will be conducted in a highfidelity simulation framework, Ambiente de Simulação Aeroespacial (ASA) [4,5], that mimics air combat dynamics, where pilots will operate alongside a loyal wingman following the evaluated metrics. The simulation scenario evaluates the feasibility and effectiveness of continuous Combat Air Patrol (CAP) operations, aiming to defend a strategic point of interest, and the Defensive Counter Air (DCA) index will be used to evaluate the performance of the human-autonomous team in achieving the mission objectives [3]. Data will be gathered via post-trial questionnaires assessing naturalness and comfort.…”

Section: User Study Experimentsmentioning

confidence: 99%

Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach

Dantas¹,

Máximo

Yoneyama

2023

ACM SIGSIM Conference on Principles of Advanced Discrete Simulation

Self Cite

View full text Add to dashboard Cite

This study proposes social navigation metrics for autonomous agents in air combat, aiming to facilitate their smooth integration into pilot formations. The absence of such metrics poses challenges to safety and effectiveness in mixed human-autonomous teams. The proposed metrics prioritize naturalness and comfort. We suggest validating them through a user study involving military pilots in simulated air combat scenarios alongside autonomous loyal wingmen. The experiment will involve setting up simulations, designing scenarios, and evaluating performance using feedback from questionnaires and data analysis. These metrics aim to enhance the operational performance of autonomous loyal wingmen, thereby contributing to safer and more strategic air combat. [Code] 1

show abstract

Section: User Study Experimentsmentioning

confidence: 99%

Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach

Dantas¹,

Máximo

Yoneyama

2023

ACM SIGSIM Conference on Principles of Advanced Discrete Simulation

Self Cite

View full text Add to dashboard Cite

show abstract

“…The capabilities of AsaBatch already supported several academic studies [4,2,12,5,6,3,8] that used the execution of thousands of simulations to achieve their results. It is worth noting that the high individual performance of each simulation is mainly due to the capabilities of MIXR itself.…”

Section: Asabatchmentioning

confidence: 99%

“…ASA has helped develop extensive academic work in the aerospace and defense context relating to different fields of study, such as artificial intelligence, machine learning, data science, and optimization. These applications can be seen in [4,2,12,5,6,3,8,9], being detailed as follows.…”

Section: Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

ASA: A Simulation Environment for Evaluating Military Operational Scenarios

Dantas¹,

Costa²,

Gomes³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The Aerospace Simulation Environment (Ambiente de Simulação Aeroespacial -ASA in Portuguese) is a custom-made objectoriented simulation framework developed mainly in C++ that enables the modeling and simulation of military operational scenarios to support the development of tactics and procedures in the aerospace context for the Brazilian Air Force. This work describes the ASA framework, bringing its distributed architecture for managing multiple simulation machines, a data analysis platform for post-processing simulation data, the capability of loading models at simulation runtime, and a batch mode execution platform to perform multiple independent executions simultaneously. In addition, we present a list of recent works using the ASA framework as a simulation tool in the air combat context.

show abstract

“…In the context of constructive simulations, in which the aircraft behave autonomously, there is a need to provide their controlling algorithms with data similar to what real pilots would receive, so that the behaviors perform in accordance [9]. One of the most important aspects that a pilot can use to decide whether to launch a missile on an opposing aircraft is the Weapon Engagement Zone (WEZ), which, in simple terms, represents the range of the weapon [10]. This definition is discussed with more depth further in Section 2.1.…”

Section: Introductionmentioning

confidence: 99%

Weapon Engagement Zone Maximum Launch Range Estimation Using a Deep Neural Network

Dantas¹,

Costa²,

Geraldo³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

This work investigates the use of a Deep Neural Network (DNN) to perform an estimation of the Weapon Engagement Zone (WEZ) maximum launch range. The WEZ allows the pilot to identify an airspace in which the available missile has a more significant probability of successfully engaging a particular target, i.e., a hypothetical area surrounding an aircraft in which an adversary is vulnerable to a shot. We propose an approach to determine the WEZ of a given missile using 50,000 simulated launches in variate conditions. These simulations are used to train a DNN that can predict the WEZ when the aircraft finds itself on different firing conditions, with a coefficient of determination of 0.99. It provides another procedure concerning preceding research since it employs a nondiscretized model, i.e., it considers all directions of the WEZ at once, which has not been done previously. Additionally, the proposed method uses an experimental design that allows for fewer simulation runs, providing faster model training.

show abstract

Engagement Decision Support for Beyond Visual Range Air Combat

Cited by 11 publications

References 31 publications

Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach

Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach

ASA: A Simulation Environment for Evaluating Military Operational Scenarios

Weapon Engagement Zone Maximum Launch Range Estimation Using a Deep Neural Network

Contact Info

Product

Resources

About