Unmanned Combat

Unmanned combat aerial vehicle (UCAV) research focuses on developing autonomous decision-making systems for air-to-air combat, primarily aiming to improve the effectiveness and survivability of these vehicles. Current research heavily utilizes reinforcement learning (RL), often employing deep reinforcement learning (DRL) architectures like deep Q-networks and transformers, along with techniques like curriculum learning and self-play to enhance training efficiency and robustness in noisy environments. These advancements are significant for improving autonomous systems' performance in complex, dynamic scenarios and have implications for both military applications and the broader field of AI, particularly in multi-agent systems and decision-making under uncertainty.

Papers

June 17, 2024

An Imitative Reinforcement Learning Framework for Autonomous Dogfight
Siyuan Li, Rongchang Zuo, Peng Liu, Yingnan Zhao
Unmanned Combat

May 28, 2024

Interpretable DRL-based Maneuver Decision of UCAV Dogfight
Haoran Han, Jian Cheng, Maolong Lv
Deep Reinforcement Learning Interpretable Way Maneuver Decision Unmanned Combat

March 17, 2024

Phasic Diversity Optimization for Population-Based Reinforcement Learning
Jingcheng Jiang, Haiyin Piao, Yu Fu, Yihang Hao, Chuanlu Jiang, Ziqi Wei, Xin Yang
Diversity Reinforcement Learning Unmanned Combat Diversity Optimization

August 7, 2023

TempFuser: Learning Agile, Tactical, and Acrobatic Flight Maneuvers Using a Long Short-Term Temporal Fusion Transformer
Hyunki Seong, David Hyunchul Shim
Animal Level Agility Agile Flight Temporal Fusion Transformer Unmanned Combat

July 12, 2023

Maneuver Decision-Making Through Automatic Curriculum Reinforcement Learning Without Handcrafted Reward functions
Zhang Hong-Peng
Reinforcement Learning Reward Function Curriculum Reinforcement Learning Maneuver Decision Unmanned 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

December 5, 2022

A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat
Jiajun Chai, Wenzhang Chen, Yuanheng Zhu, Zong-xin Yao, Dongbin Zhao
Reinforcement Learning Action Space REinforcement Learning Unmanned Combat Fictitious Self Play

June 26, 2022

Object Detection and Tracking with Autonomous UAV
A. Huzeyfe Demir, Berke Yavas, Mehmet Yazici, Dogukan Aksu, M. Ali Aydin
Unmanned Aerial Vehicle Autonomous Navigation Web Tracking Simulation Environment Unmanned Combat

January 14, 2022

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

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

Unmanned Combat

Papers

An Imitative Reinforcement Learning Framework for Autonomous Dogfight

Interpretable DRL-based Maneuver Decision of UCAV Dogfight

Phasic Diversity Optimization for Population-Based Reinforcement Learning

TempFuser: Learning Agile, Tactical, and Acrobatic Flight Maneuvers Using a Long Short-Term Temporal Fusion Transformer

Maneuver Decision-Making Through Automatic Curriculum Reinforcement Learning Without Handcrafted Reward functions

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

A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat

Object Detection and Tracking with Autonomous UAV

Reinforcement Learning based Air Combat Maneuver Generation

Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combat