Presentation
Beyond Human Actors: Leveraging AI for Enhanced Public Safety XR Training
DescriptionLaw enforcement officers (LEOs) and community partners frequently serve as first responders to 911 calls, many of which involve behavioral health crises. Approximately 20% of these service requests pertain to individuals with mental health conditions, who are estimated to face an 11.6-fold higher risk of police use of force than the general population. Integrating extended reality (XR) technologies holds significant promise for enhancing police decision-making, particularly by supporting the effective application of de-escalation tactics in high-stakes situations. Despite this potential, current XR-based training scenarios for LEOs often fall short, lacking the diversity and realism necessary to address the complex demands of de-escalation-especially the need for real-time, high-stress interactions that are essential for skill development under pressure. In this work, we leverage artificial intelligence (AI)-driven training within XR environments to address these shortcomings. Our approach involves a two-phase evaluation of an AI-Non Playable Character (NPC)-based XR training prototype, focusing first on technological usability with non-LEOs, and then on training efficacy with LEOs. Results demonstrate increased user engagement, a stronger sense of VR presence, and minimal discomfort. Additionally, participants exhibited higher germane and lower extrinsic cognitive load, with LEOs showing a 50% reduction in race and gender bias according to IAT scores.
Contributors
Alternate Presenter
Event Type
Industry/Practitioner Content
Lecture
TimeWednesday, October 15th1:30pm - 1:50pm CDT
LocationGrand Hall K
Extended Reality