When police officers interact with someone during a traffic stop or just a resident in need of help, it’s hard to know ahead of time if that person is autistic, otherwise neurodivergent or has a disability that requires a more specific response.<\/p>\n
Now officers in the Fort Worth Police Department are practicing those types of interactions \u2014 and learning the signs of various conditions \u2014 without putting anyone in harm’s way. <\/p>\n
A new AI training tool developed by a professor at the University of Texas at Arlington is simulating these training scenarios for officers. <\/p>\n
“We can create lots of different difficulty levels for the officers who are training,” says Dr. Shuchi Deb, an associate professor in UT Arlington’s Department of Industrial, Manufacturing and Systems Engineering. “Some of the AI can be very compliant, some of them are not that compliant, some of them can be impossible to de-escalate.”<\/p>\n
Fort Worth police officer Jorge Lopez worked with Deb to develop the training and says there are obvious advantages to employing AI.<\/p>\n
“With AI, it takes out the need for a physical human role player, it takes out safety considerations because there’s no physicality to it,” he says. “So, it’s something that we can do a lot more often in training.”<\/p>\n
The program is also able to give officers real time feedback about their approach to a situation. <\/p>\n
“The AI tool also evaluates what the officer is saying and based on that, it scores their statement as a positive or a negative statement,” Deb said. “So officers can see that scoring on their headset in real time for every statement they are saying.”<\/p>\n
Officers also receive an in-depth analysis of how they approached the simulation at the end of the exercise. <\/p>\n
Ron Corning is a co-host of KERA’s NTX Now. Got a tip? Email Ron at\u00a0rcorning@kera.org<\/a>.<\/p>\n