Air Combat

Air combat research focuses on developing autonomous agents capable of realistic and effective maneuvers in simulated environments, primarily to improve pilot training and explore novel tactics. Current efforts leverage machine learning, particularly reinforcement learning and deep learning architectures like neural networks and graph attention networks, to model complex flight dynamics and decision-making in both within-visual-range and beyond-visual-range scenarios. This research is significant for enhancing the realism and efficiency of pilot training simulations, potentially leading to improved tactical strategies and more effective autonomous systems for air defense.

Papers

January 8, 2025

Cluster & Disperse: a general air conflict resolution heuristic using unsupervised learning
Mirmojtaba Gharibi, John-Paul Clarke
Unsupervised Learning Cluster Structure Scalable Algorithm Air Combat Dispersion Profile

May 13, 2024

Fighter flight trajectory prediction based on spatio-temporal graphcial attention network
Yao Sun, Tengyu Jing, Jiapeng Wang, Wei Wang
Graph Attention CNN LSTM Air Combat Aircraft Trajectory Flight Trajectory Prediction

April 22, 2024

A survey of air combat behavior modeling using machine learning
Patrick Ribu Gorton, Andreas Strand, Karsten Brathen
Machine Learning Timely Survey Multi Agent Learning Behavior Model Air Combat

March 26, 2024

BVR Gym: A Reinforcement Learning Environment for Beyond-Visual-Range Air Combat
Edvards Scukins, Markus Klein, Lars Kroon, Petter Ögren
Air Combat

February 7, 2024

Deep Learning Based Situation Awareness for Multiple Missiles Evasion
Edvards Scukins, Markus Klein, Lars Kroon, Petter Ögren
Unmanned Aerial Vehicle Situational Awareness Pursuit Evasion Air Combat

September 20, 2023

Hierarchical Multi-Agent Reinforcement Learning for Air Combat Maneuvering
Ardian Selmonaj, Oleg Szehr, Giacomo Del Rio, Alessandro Antonucci, Adrian Schneider, Michael Rüegsegger
Multi Agent Reinforcement Learning Heterogeneous Agent Air Combat

April 27, 2023

Learning Environment for the Air Domain (LEAD)
Andreas Strand, Patrick Gorton, Martin Asprusten, Karsten Brathen
Imitation Learning Behavior Model Educational Technology Air Combat

April 19, 2023

Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach
Joao P. A. Dantas, Marcos R. O. A. Maximo, Takashi Yoneyama
Deep Reinforcement Learning Autonomous Agent Deep Reinforcement Learning Approach Air Combat

March 6, 2023

Reinforcement Learning Based Self-play and State Stacking Techniques for Noisy Air Combat Environment
Ahmet Semih Tasbas, Safa Onur Sahin, Nazim Kemal Ure
Reinforcement Learning Robust Reinforcement Learning State Abstraction Air Combat Unmanned Combat Self Play Reinforcement Learning

February 12, 2023

Maneuver Decision-Making For Autonomous Air Combat Through Curriculum Learning And Reinforcement Learning With Sparse Rewards
Yu-Jie Wei, Hong-Peng Zhang, Chang-Qiang Huang
Reinforcement Learning Curriculum Learning Sparse Reward Maneuver Decision Air Combat Unmanned Combat

October 13, 2022

Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircrafts
Muhammed Murat Özbek, Süleyman Yıldırım, Muhammet Aksoy, Eric Kernin, Emre Koyuncu
Reinforcement Learning Deep Reinforcement Learning Plane Feature Air Combat

July 9, 2022

Supervised Machine Learning for Effective Missile Launch Based on Beyond Visual Range Air Combat Simulations
Joao P. A. Dantas, Andre N. Costa, Felipe L. L. Medeiros, Diego Geraldo, Marcos R. O. A. Maximo, Takashi Yoneyama
Machine Learning Machine Learning Model Supervised Machine Learning Air Combat Resampling Technique

January 14, 2022

Reinforcement Learning based Air Combat Maneuver Generation
Muhammed Murat Ozbek, Emre Koyuncu
Reinforcement Learning Air Combat Unmanned Combat Delayed Deep Deterministic Policy Gradient

December 1, 2021

Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combat
Yiwen Zhu, Zhou Fang, Yuan Zheng, Wenya Wei
Reinforcement Learning Maximum Entropy Soft Actor Critic Air Combat Unmanned Combat Homotopy Optimization

November 4, 2021

Engagement Decision Support for Beyond Visual Range Air Combat
Joao P. A. Dantas, Andre N. Costa, Diego Geraldo, Marcos R. O. A. Maximo, Takashi Yoneyama
Decision Support Air Combat

Air Combat

Papers

Cluster & Disperse: a general air conflict resolution heuristic using unsupervised learning

Fighter flight trajectory prediction based on spatio-temporal graphcial attention network

A survey of air combat behavior modeling using machine learning

BVR Gym: A Reinforcement Learning Environment for Beyond-Visual-Range Air Combat

Deep Learning Based Situation Awareness for Multiple Missiles Evasion

Hierarchical Multi-Agent Reinforcement Learning for Air Combat Maneuvering

Learning Environment for the Air Domain (LEAD)

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

Reinforcement Learning Based Self-play and State Stacking Techniques for Noisy Air Combat Environment

Maneuver Decision-Making For Autonomous Air Combat Through Curriculum Learning And Reinforcement Learning With Sparse Rewards

Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircrafts

Supervised Machine Learning for Effective Missile Launch Based on Beyond Visual Range Air Combat Simulations

Reinforcement Learning based Air Combat Maneuver Generation

Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combat

Engagement Decision Support for Beyond Visual Range Air Combat