Meiyi Ma, assistant professor of computer science at Vanderbilt, is leading research funded by a $300,000 National Science Foundation grant to develop what's considered the world's first Generative Artificial Intelligence (GenAI) training system for 911 call takers and dispatchers.
The work is a collaboration between Ma's lab and the Nashville Department of Emergency Communications (DEC). Gautam Biswas, Cornelius Vanderbilt Professor of Engineering, and DEC director Stephen Martini are co-principal investigators.
Nationwide, the training of public safety dispatchers is a continual effort. However, conducting these training exercises can be laborious and time-consuming. They involve multiple experienced employees acting as role-players to simulate service calls, allowing trainees and trainers to practice call-processing skills and assess performance. Additionally, the quality of training can vary based on available resources and the trainers' experience. Many dispatching centers, particularly in areas with limited resources, struggle with heavy workloads and insufficient training.
"Simulation training provide realistic, immersive scenarios allowing our team members to practice their life-saving skills using the tools they interact with every day," Martini said. "Engaging simulation allows trainees and trainers to train more robustly in a shorter time producing better prepared dispatchers in a faster and more efficient manner."
Ma and her team intend for the GenAI training system to address these issues through three essential functions: playing the role of callers and simulating 911 calls from a broad and diverse spectrum of emergency scenarios; effectively evaluating the dispatcher's performance in the simulation; and providing strategies for training enhancement.
"Nearly 6,000 emergency communications centers could benefit from this training opportunity," Ma said. "We are thrilled to collaborate with our Metro Nashville DEC team to create innovative and trustworthy technologies to support emergency response and public safety since 2021. Moreover, the GenAI-enabled solution has the potential to extend beyond emergency services to other training domains, such as education and healthcare. This initiative can also serve as a valuable resource for governments in shaping policies around using AI and GenAI technologies."
The joint venture is the first Vanderbilt-Metro Nashville government project since the formation of the Nashville Innovative Alliance, which seeks to bring together public, private, civic and education institutions to enhance the region's innovation ecosystem.
"Congratulations to Professor Ma and her team for pioneering a transformative GenAI training approach," said Padma Raghavan, vice provost for research and innovation and chief research officer. "I'm proud that Vanderbilt's Generative AI Seed Grant could help catalyze such impactful research, with the potential to revolutionize public safety training worldwide."
Earlier this year, Ma was one of six people to receive a Seed Grant. The grant fund was designed to foster groundbreaking work in large language models (LLMs), like ChatGPT and Bard.
