acm-header
Sign In

Communications of the ACM

ACM TechNews

Nasa AI to Power First-Responder Tech


View as: Print Mobile App Share:
An artificial intelligence solution under development could help first responders achieve situational awareness more efficiently.

The U.S. National Aeronautics and Space Administration's Jet Propulsion Laboratory is working on an artificial intelligence solution to help local law enforcement, firefighters, and other first responders filter the clutter of available information to ach

Credit: Razum/Shutterstock

First responders are set to benefit from the U.S. National Aeronautics and Space Administration's (NASA) effort to extract insights from its 500-terabyte and growing Planetary Data System.  

NASA's Jet Propulsion Laboratory (JPL) is working on an artificial intelligence (AI) solution called Assistant for Understanding Data through Reasoning, Extraction, and sYnthesis (Audrey), which can filter the clutter of information available to first responders and help them achieve situational awareness.  A lightweight component of cloud-based software that can operate on an ordinary personal computer, Audrey is envisioned as a next-generation architecture that runs on a distributed basis.

"We can make intelligent decisions without knowing everything around the world," says JPL's Ed Chow. He notes Audrey would teach itself based on the data that it has access to, instead of having programmers create AI software for every problem.  

The solution has facial-recognition capability, but also the ability to read and understand documents, do intelligence fusion and synthesis, and communicate inferences to users.  The idea is to provide every first responder in a department with customized, targeted intelligence and advice in natural language via an earpiece.  

The U.S. Department of Homeland Security's John Merrill believes a live solution could be running in two years.

From Federal Computer Week
View Full Article

 

Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account