Cognitive Assistance for Firefighting Multidomain Operations Using Reinforcement Learning and Generative AI

There is unprecedented growth and severity in wildland fire activity across the world with greater socio-, economic, and environmental impact. In 2021, Lockheed Martin initiated an internal development program, the Cognitive Mission Manager (CMM), to demonstrate and provide a tool that uses multi-domain operations and machine learning to support wildland fire missions. Over three years, the CMM developed a cognitive assistant for firefighter operations, which includes creating a digital twin of an entire wildland fire incident by fusing real-world data from satellites, aircraft, and ground assets into a system-of-systems and environmental digital twin in NVIDIA Omniverse. Through this digital twin, CMM is able to show predictions of fire spread and use reinforcement learning to provide recommended courses of action. In 2024, the CMM team further matured the reinforcement learning and began implement generative-AI capabilities. With these advances in AI technologies, firefighting and other complex operational environments could be standing on the precipice of a monumental tipping point that improves the use of data from satellites and other sources. This paper will discuss how the developed services reconstruct actual wildland fire incidents in a three-dimensional space to create a digital twin. It will also explore how reinforcement learning and generative AI can enhance and leverage digital twins and improve user experiences within these scenes.