Towards Human Engagement with Realistic AI Combat Pilots

2025/09/30 by Selmonaj, Ardian, Del Rio, Giacomo, Schneider, Adrian +1
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2509.26002

Abstract

We present a system that enables real-time interaction between human users and agents trained to control fighter jets in simulated 3D air combat scenarios. The agents are trained in a dedicated environment using Multi-Agent Reinforcement Learning. A communication link is developed to allow seamless deployment of trained agents into VR-Forces, a widely used defense simulation tool for realistic tactical scenarios. This integration allows mixed simulations where human-controlled entities engage with intelligent agents exhibiting distinct combat behaviors. Our interaction model creates new opportunities for human-agent teaming, immersive training, and the exploration of innovative tactics in defense contexts.

Citations

• Loyal Wingman Assessment: Social Navigation for Human-Autonomous Collaboration in Simulated Air Combat
• BVR Gym: A Reinforcement Learning Environment for Beyond-Visual-Range Air Combat
• Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach
• The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

Related

• Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach
• Coordinated Strategies in Realistic Air Combat by Hierarchical Multi-Agent Reinforcement Learning
• Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning
• Enhancing Aerial Combat Tactics through Hierarchical Multi-Agent Reinforcement Learning
• Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircrafts