Jul 29, 2021 | Atlanta, GA
A team of researchers led by Sonia Chernova, associate professor of interactive computing at Georgia Tech, has won a five-year, $20 million grant from the National Science Foundation to build intelligent systems that support aging. The grant’s co-PI is Elizabeth Mynatt, director of the Institute for People and Technology (IPaT) at Georgia Tech—IPaT’s expertise in technology for “aging in place” will play a key role in the funded research program.
The grant will support the creation of the NSF AI Institute for Collaborative Assistance and Responsive Interaction for Networked Groups, or AI-CARING. The institute aims to develop new longitudinal, collaborative AI systems that work with aging adults including those diagnosed with mild cognitive impairment, and their caregivers.
Most older adults prefer to remain in their own homes. But safety concerns, medication schedules, and isolation can all make it difficult for them to do so.
“Imagine an aging parent who no longer remembers to turn the stove off after cooking,” said Mynatt. “An intelligent system could support meal preparation activities, such as reminding older adults warm up a prepared meal, detecting when the stove is left on, and sending a reminder to turn it off. Then, if the stove wasn’t turned off, the system could send an alert to a caregiver.”
Now, imagine that system extended to support a full calendar of appointments, medication reminders, and schedules for multiple caregivers, among other things.
“Our goal is to create systems that help people take care of people,” Mynatt said. “Care can be a complicated task, requiring coordination and decision making across family members managing day to day demands.”
“This kind of personalized AI presents a fascinating series of technical challenges as well,” Chernova said. “Most AI agents focus on a single choice or action — a sale, for example — and then use data from as many people as possible to understand it. But in this case, the AI is gathering in-depth data on a single person and their care team.”
“We need AI systems that can interact with users over weeks or months or even years,” Chernova said. “And in order to help someone, you need to understand their values and their relationships with other people.”
“The goal is emphatically not to replace human caretakers,” Chernova said, but to lend them a hand.
“AI is not going to become a home nurse,” she said. “Caring for an older relative or friend can be overwhelming. Our AI system seeks to support human caregivers by offloading some of the logistics and reminders, so that people can focus on the more positive aspects of care.”
The award builds upon decades of work at Georgia Tech, both in artificial intelligence, and — through IPaT— understanding the technological needs of older adults. The new systems will be tested with Georgia families through existing programs, including the Emory-Georgia Tech Cognitive Empowerment Program, which currently serves over 100 people diagnosed with mild cognitive impairment.
“The AI-CARING Institute builds on our existing strengths in AI and in technology for aging. It will create not only novel solutions but a new generation of researchers focused on the interaction between the two,” said Charles Isbell, dean and John P. Imlay, Jr. Chair of Computing. “Our aim in the College of Computing is to build cutting-edge technologies that improve the lives of everyone, and I can’t think of a better example than AI-CARING.“
“I am delighted to announce the establishment of new NSF National AI Research Institutes as we look to expand into all 50 states,” said National Science Foundation Director Sethuraman Panchanathan. “These Institutes are hubs for academia, industry, and government to accelerate discovery and innovation in AI. Inspiring talent and ideas everywhere in this important area will lead to new capabilities that improve our lives from medicine to entertainment to transportation and cybersecurity and position us in the vanguard of competitiveness and prosperity.”
AI-CARING will include faculty from Georgia Tech, Carnegie Mellon University, Oregon State University, the University of Massachusetts-Lowell and Oregon Health & Science University, and has Amazon and Google as industry sponsors. The core researchers will connect with other higher education institutions, nonprofits, and government entities across the country in order to provide education and workforce opportunities to diverse groups.
In partnership with the United States Department of Agriculture, the National Institute of Food and Agriculture, the U.S. Department of Homeland Security Science & Technology Directorate, and the U.S. Department of Transportation Federal Highway Administration, the NSF is funding 11 centers within its National AI Research Institutions program. Georgia Tech has been awarded two of the grants: AI-CARING and AI4Opt, or AI for Advances in Optimization, led by PI Pascal Van Hentenryck, the A. Russel Chandler III chair of Industrial and Systems Engineering.