Someday, socially engaging robots that provide an individualized curriculum for every student could transform the future of education, Terrence J. Sejnowski tells the Dana Foundation in an interview this week. Sejnowski founded Neural Computation, the top journal in neural networks and computational neuroscience, and has developed pioneering algorithms for decades.
In this Q&A, he talks about these and the results of his recent paper in Science magazine, “Foundations for a New Science of Learning.” Robot-interaction researchers started at the beginning, trying to figure out how to keep toddlers engaged with Rubi the robot before they could try to teach them anything. For example:
The first problem Javier [the researcher] encountered upon introducing Rubi the robot into the preschool environment was that the children pulled off the robot’s arms. The children saw it as a toy and wanted to see if they could pull it apart. To solve that problem, he programmed the robot to cry whenever the pressure reached a certain threshold. So the child would back off, because crying is a social signal for “hurt.” If the robot kept crying, the child would hug it, because that’s the way that children communicate with adults when they are hurt. Even at this young age, the child is able to pick up social cues, especially emotional ones.
The interview really gets going when he talks about the kids, like how Rubi needed to respond “not too quick, not too slow” to maintain their attention. PNAS hosts 5 little videos of toddlers and the robot; I like “night-night” and “giggling” best.
Post a Comment