This robot tutor detects the 'emotional state' of its pupils

Teachers, watch out - your jobs could be next in line for the inevitable robot takeover. Spanish AI researchers have developed software that can take a pupil's emotional state into account when teaching them.

It's the work of Imbernòn Cuadrado and his co-workers at the Department of Artificial Intelligence in Madrid. While digital educational resources are becoming increasingly common in schools, they tend to treat every child identically. As any teacher knows, that's a recipe for inattention at best, and misbehaviour at worst.

But Cuadrado's system, named ARTIE, is different. "The main goal of our work was to design a system that can detect the emotional state of primary school children interacting with educational software and make pedagogic interventions with a robot tutor that can ultimately improve the learning experience," he said.

Effective Support

Rather than trying to identify specific emotions, it uses keyboard strokes and mouse actions to figure out whether a child is concentrating, distracted or inactive. Those can then be used to trigger different kinds of intervention - encouragement, or attempts to raise interest or motivation - from a robot tutor.

In tests on two primary school volunteers, the kids said they enjoyed having a robot to guide their learning and preferred it to working alone. But human teachers shouldn't worry too much - the kids also said they felt like they'd have learnt more with their normal teacher.

"We consider that robot tutors could have an effective support role to play in the primary school classroom in helping children reach their specific learning objectives," said Cuadidro.

He added: "Our first prototype was designed to demonstrate that the architecture works in detecting simplified emotional states. The next step will be to implement methods for detecting a more complex range of emotions with cameras and microphones and to test the longer term impact of robot tutors on children's learning curves."

The full details of the research have been published in Frontiers in Computational Neuroscience.

Duncan Geere
Duncan Geere is TechRadar's science writer. Every day he finds the most interesting science news and explains why you should care. You can read more of his stories here, and you can find him on Twitter under the handle @duncangeere.