A fire alarm jolts you from your office desk, and you head for the nearest exit. But what if the closest exit has already been blocked by the fire?
Researchers at the National Institute of Standards and Technology (NIST) and their colleagues have developed a new AI model called Safe Step that can redirect occupants to the safest evacuation route in a fire. Described in the Journal of Building Engineering, the model can be used with electronic displays to show whether an exit is safe to use.
“Fires can grow and spread,” said Hongqiang “Rory” Fang, a research associate at NIST and first author of the journal paper. “Our model forecasts how the fire is evolving and can help update emergency exit displays to direct people toward the safest exit.”
Safe Step can be used in “smart” buildings, where sensors monitor real-time environmental conditions, such as temperature and air quality. Some of these buildings are testing a new technology called a dynamic emergency exit display, which can indicate that the exit is safe to use or point arrows to a safer route out of the building.
Previous research has proposed using traditional algorithms to find the shortest path for safely evacuating a building fire. However, these algorithms depend entirely on current building conditions and do not consider the cumulative hazards that evacuees can face along the route.
“We asked ourselves, ‘Can we build a better algorithm that predicts how the fire evolves, and in a way that helps save more lives?’” said NIST mechanical engineer Wai Cheong Tam.
Machine Learning for Safe Evacuations
Their model, Safe Step, uses a type of AI known as reinforcement learning. It makes decisions on the safest routes through trial and error. Safe Step uses the building layout to learn evacuation routes and data from a NIST fire simulation tool to anticipate how a fire in the layout develops over time.
During training, the model learns to forecast how a fire will affect occupants and then guides them to safer evacuation routes. In real-world use, the model does not need to run a simulation of the fire in real time. Instead, it would rely on live sensor data from the building to continuously adjust its recommendations as the fire evolves.
The algorithm needs numbers, though, to determine whether it’s choosing the best route. So NIST researchers used a fire safety metric called the fractional effective dose (FED) of toxic gases. This variable represents the severity of fire hazards to which a person is exposed over time. The lower the FED, the lower the hazard exposure for the occupants. The model chooses the route with the lowest FED, accounting for how toxic gas exposure changes over time as an occupant moves.
Researchers then used the model in two test cases to compare with the traditional algorithm. They also used a more complex single-level building structure and found that the model consistently gave safe evacuation routes.
For example, suppose a fire starts in a room across the hallway, and a small amount of smoke spreads into the hallway. A traditional algorithm would guide the occupant to cross the hallway to get to the closest exit. But what happens if the fire continues to grow and becomes extremely dangerous by the time the occupant crosses the hallway and approaches the exit? That nearest exit is no longer a safe option. Safe Step can anticipate this change and provide data for dynamic exit signs to direct the occupant to a more distant but safer exit at the opposite end of the hallway.
Safe Step’s Next Steps
The current model works for a single-story floor plan. Researchers’ next steps include improving the model’s capabilities to handle multilevel building structures, where an evacuee can go up or down a floor in addition to turning left or right down a hallway.
To most accurately model the evacuation of multiple individuals, researchers plan to build an AI system that has what is known as multiple agents, with each agent corresponding to a different building occupant. Interactions among multiple agents will make the model more adaptable to real fire response and evacuation scenarios.
For instance, during a fire, congestion can build up at the building’s entrance as multiple people try to exit at the same time. This creates a bottleneck, but with an improved algorithm, the model could direct evacuees to different exits while coordinating access points for firefighters to enter the building. This would make it easier for firefighters to extinguish the fire or rescue vulnerable individuals, such as older adults, children and people with disabilities.
NIST has more than a century of experience working with other organizations to advance fire safety research. In just the last several decades, by improving smoke alarms and firefighter gear, NIST’s fire research has played a crucial role in reducing fire-related deaths each year.
Researchers estimate that technologies like Safe Step could start appearing in five to 10 years, though widespread adoption will depend on regulatory approval, reliability testing and integration with existing safety systems.
“This research is still in the early R&D stage, but it represents an important step toward intelligent firefighting where effective use of advanced technologies can protect property and save lives,” said Fang.
Paper: Hongqiang Fang, Wai Cheong Tam, Ruggiero Lovreglio, Md. Ismail Siddiqi Emon and Michael Xuelin Huang. Development of a tenability-based path planning model for building fire evacuations using reinforcement learning. Journal of Building Engineering. Published online Jan. 15, 2026. DOI: 10.1016/j.jobe.2025.115132
Source: NIST