Towards Human Engagement with Realistic AI Combat Pilots
This work addresses the need for immersive training and human-agent teaming in defense contexts, though it is incremental as it builds on existing simulation tools and reinforcement learning methods.
The paper tackles the problem of enabling real-time interaction between humans and AI agents in simulated air combat, resulting in a system that integrates trained agents into a defense simulation tool for mixed simulations.
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.