Newswise — AMES, Iowa – Researchers at Iowa State University are creating a system that will provide students, teachers, police officers and others with accurate, real-time information in the event of an active shooter in a school. 

Soumik Sarkar, an associate professor of mechanical engineering, is serving as the lead investigator for a nearly $650,000 project sponsored by the National Science Foundation and titled “Active Shooter Tracking & Evacuation Routing for Survival (ASTERS).” Co-investigators on the project include Stephen Gilbert, associate professor of industrial and manufacturing systems engineering; and Joanne Marshall, associate professor in the School of Education. 

The researchers will develop the technology, which will track a shooter in real time across multiple cameras and microphones, and calculate the optimal evacuation path to safety for each student, teacher and staff member. The program will communicate this information through a mobile app that will be co-created in partnership with a community of students, parents, educators and administrators as well as school resource and safety officers. 

Sarkar will provide expertise to the project in the areas of multi-modal sensing, artificial intelligence (AI) and machine learning. 

“ASTERS is about building a decision system that will incorporate multi-modal sensing, AI and machine learning techniques to accurately localize a gunman and weapons while preserving privacy of school community members,” he said. “It will also use new computer vision and high-performance computing solutions to estimate crowd density and movement of people, and novel optimization and real-time simulation algorithms to predict ideal evacuation routes based on the building layout and predicted movement of the shooter.” 

Gilbert will examine the project from a cognitive engineering perspective. 

“After the intelligent surveillance system can calculate the optimal evacuation routes, we have to communicate those to panicked people,” he said. “That’s where I will be applying principles from cognitive engineering. Communicating an evacuation route during a panicked time is a cognitive challenge because when people won’t spend much time to think, they’ll just act, so we don’t have a lot of time and we need to get it right.”

Marshall will study ways the ASTERS protocol can be applied in pK-12 contexts and will work with a school in Iowa to test the protocol during the last year of the three-year project. 

“Building a system such as ASTERS demands a range of expertise from computer science, human-machine interaction, and engineering to social science and education. Therefore, inter-departmental and inter-college collaboration is indispensable in this case,” Sarkar said. 

The project will also rely on the expertise of Darin Van Ryswyk, an Iowa State deputy chief of police, who will help the researchers understand the mindset of first responders during school-shooter crises, what they are trained to do and how ASTERS might help them. 

The team will also work with researchers from the University of Tennessee. Subhadeep Chakraborty, associate professor of mechanical, aerospace and biomedical engineering will serve as the lead investigator at the Tennessee site. His previous experience involves calculating optimal evacuation paths under different contexts. Michael Olson, professor of psychology at Tennessee, will apply findings from his past research, which has studied how cognition works when an individual is panicked. 

One advantage of this inter-university collaboration is that it will allow the researchers to examine a variety of school settings in both urban and rural areas, according to Gilbert. The research team hopes that one day this research can be applied to other active-shooter situations at places other than schools. 

“ASTERS is important for saving lives under a life-and-death situation,” Gilbert said. “Plus, figuring out how to communicate most effectively with a crowd that’s panicked could be useful in many circumstances outside schools.”

 

– 30 – 

Grant No Link: NSF 1932033