Two researchers at the University of Wisconsin-Madison have created a robotic teacher that can gauge students' level of attention and use some of the same techniques as human teachers to bring it back, according to the United Kingdom-based New Scientist. The researchers, Bilge Mutlu and Dan Szafir, have been testing whether a robot teacher could help boost how much students retain from lessons.
"We wanted to look at how learning happens in the real world," Mutlu told New Scientist. "What do human teachers do and how can we draw on that to build an educational robot that achieves something similar?"
In one test, Mutlu and Szafir had their robot tell students a story in a one-on-one situation and used sensors on the students to monitor the area of their brains that manages learning and concentration. Every time the sensor detected that a student's attention level had decreased, the robot would receive a signal prompting it to try something new to recapture the student's attention, such as raising its voice or using arm gestures.
With other students, the researchers had the robot refrain from gesturing or changing its voice when a student's attention level dropped. After the storytelling was over, all students were asked a series of questions about the story they were told. The researchers found that the students who were given a cue from the robot every time their attention level dropped answered more questions correctly than the students who did not receive cues from the robot.
Andrew Ng, director of Stanford University's Artificial Intelligence Lab and co-founder of online classroom Coursera, believes the idea of using automation to promote student engagement in this way could have "significant implications for the field of education," according to the New Scientist.
"The vision of automatically measuring student engagement so as to build a more interactive teacher is very exciting," said Ng.