According to new research, robots can take only three hours to productively learn techniques that can be used to help teachers in a classroom setting. The research, published in Science Robotics, saw a robot being automated to gradually learn autonomous behavior from human guidance and demonstrations.
A human teacher supervised the robot, teaching it how to help young pupils in a learning activity, and it was then able to support the children in the same activity independently. The advice it consequently provided was shown to be constant with that offered by the teacher.
Researchers say the technique could have numerous benefits to teachers, as they face growing demands on their time, and could be constructive for pupils, with research formerly showing that using robots together with teachers in the classroom can have benefits for their education.
They also believe it holds substantial potential for a number of other sensitive uses of social robots, such as in assistive and eHealth robotics.
The study was organized by researchers at the University of Plymouth, which has an extensive history of developing social robots for a range of health and education settings, working with associates at the University of Lincoln and the University of the West of England.
Through a series of assessments, they analyzed a system called SPARC (Supervised Progressively Autonomous Robot Competencies) and proved that in a little over three hours, the robot could be successfully trained by the teacher to support an educational activity.
While the autonomous robot used actions with a different frequency than the teacher, it only used actions already shown, learned the unique dynamics related to each type of action, and its behaviour had a positive influence on the children. Certainly, the robot was also able to effectively learn how to support children with social actions, like encouragements and praise.
The Advantages of Robots Inside Classrooms
The researchers say this could prove especially useful in future human-robot communications because it would enable scientists to avoid the standard approach to designing robotic controllers, whereby domain experts define a behaviour to be implemented by engineers. Rather this approach enables end-users to directly teach a robot.
Dr Emmanuel Senft, who headed the study as part of his PhD research, said: “Creating autonomous social robot behaviours is a central challenge in social robotics, in both ethical and technical terms. My dream is that everyone should be able to benefit from robots, not only engineers, and I think letting people to teach robots to interact is the way to go. I hope the method we have offered here could work in that matter and be applied to a vast range of situations, for social and non-social robots.”
YOU MAY LIKE: How can technology help education?
Professor Tony Belpaeme, from the Ghent University and University of Plymouth, has worked in the field of social robotics for about two decades and was also involved in the study. He added: “The benefits of using robots to help in a classroom site are there for everyone to see. But how to set them to work so they provide constant support to pupils, in a way that teachers can trust, is a real test. This study is certainly a progressive step towards that. However, one unanticipated thing it did show is we perhaps need to construct greater acceptance and trust among teachers themselves as they said it did not result in a decline to their workloads.”