Emory and Georgia Tech AI automates cognitive tests for wild capuchin monkeys

Scientists at Emory University and the Georgia Institute of Technology built CapuchinAI, an AI system that uses facial recognition and real-time touchscreen testing to automate cognitive studies of capuchin monkeys in the wild, phys.org reported. A proof-of-concept appears in the American Journal of Primatology. The platform integrates a compact, battery-powered computing system into a field research setup. It identifies an approaching monkey, presents a learning task tailored to that individual on a touchscreen, and automatically delivers a food reward when the animal performs the task correctly. Field tests of the prototype in the Taboga Forest Reserve of Costa Rica found CapuchinAI identifies individual capuchins with 97% accuracy after training on still images and videos. Wild capuchins rapidly habituated and learned touchscreen-reward associations, the teams said, offering a scalable field method for cognitive testing and mapping individual differences. Senior author Marcela Benítez, an Emory assistant professor of anthropology, said primate cognition is rarely studied in the wild because experimental control is hard in unpredictable environments, even though primate brains evolved outside the lab. First author Federico Sánchez Vargas, an Emory Ph.D. student in anthropology, said the method lets researchers automate testing of individuals already known from field observation and quantify results in natural settings. Co-authors include Jacob Abernethy, a Georgia Tech associate professor of computer science, and Sai Rakshith Potluri, a former Georgia Tech graduate research assistant. The open-source paper includes coding guidance and a blueprint for a low-cost field platform. DOI: 10.1002/ajp.70194. Field primatology groups gain a repeatable, automated way to measure individual cognition outside captivity, expanding comparative data that lab-only designs miss.