Cognitive Assistance for Firefighting Multidomain Operations Using Reinforcement Learning and Generative AI
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it