Much of the discussion around artificial intelligence has been around how many jobs will be lost as a result of automation rather than any discussion about the ways AI will improve our ability to work safely and effectively.

A good example of this comes from research undertaken by the Jet Propulsion Laboratory that looked at how AI can be used to collect building data to help keep fire fighters safe when they enter an inferno.

They developed a system called AUDREY, which stands for Assistant for Understanding Data through Reasoning, Extraction and sYnthesis, in conjunction with the Department of Homeland Security.

Smarter fire fighting

AUDREY is capable of tracking the team of firefighters as they enter a building, all the time sending them data that is personalized to their location in the facility.  It is even capable of giving them recommendations on where and what to do next.

“As a firefighter moves through an environment, AUDREY could send alerts through a mobile device or head-mounted display,” the team say.

They suggest that sensors built into the firefighters clothing could pick up everything from their location to the heat in rooms and the presence of any chemicals or gases.

“When first responders are connected to all these sensors, the AUDREY agent becomes their guardian angel,” they continue. “Because of all this data the sensor sees, firefighters won’t run into the next room where the floor will collapse.”

Technological advances

The team laud the way technology is providing a constant stream of support to first responders live in the field.

“The proliferation of miniaturized sensors and Internet of Things devices can make a tremendous impact on first responder safety, connectivity, and situational awareness,” they say. “The massive amount of data available to the first responder is incomprehensible in its raw state and must be synthesized into useable, actionable information.”

The system is designed to provide support from the cloud, both by sending data to firefighters, but also by monitoring the data and making predictions about how to respond to what it sees unfolding.

What’s more, AUDREY is capable of understanding what role each firefighter has and thus provide the right information at the right time.

“Since AUDREY knows the roles of everyone who receives her data, she only supplies the relevant information that is appropriate for them,” they say.

The system was put through its paces in a virtual demonstration in June, and the team hope to test it in a live environment within the next year.

Suffice to say, as with any AI system at the moment, it can only work if it has great data to work with, but the team are confident that AUDREY has both that and the logic engine underpinning the data to be of real use to firefighters.

“Most A.I. projects are rule-based—if this, then that,” they say. “But what if you’re only getting part of the information? We use complex reasoning to simulate how humans think. That allows us to provide more useful info to firefighters than a traditional A.I. system.”