The ALIZ-E (an open source platform for biometric authentication) Nao robots stand 60cm tall and use speech recognition software to provide personalised responses and interactions with children.
The project, led by the UK’s Plymouth University initially began in 2010 and aimed to develop artificial intelligence for small robots and to measure how children interact with and learn from these robots. Although at the time ALIZ-E was able to create such robots, the interaction period was limited to several minutes. A long-term human-robot interaction has the potential to enable real bonds with people, which can in turn be used to offer support and education.
For example, the Nao robots worked with children with diabetes by offering training and entertainment. Children were able to play quizzes and games with the robots, while also dancing with them and increasing their understanding of their illness, and how they could better manage their condition.
The robots also helped children with keeping a diary in which they recorded food intake, insulin injections and blood sugar levels all associated with diabetes. The study has proved that children are more eager to provide information if prompted to do so by a robot
“In many cases where a child has diabetes, you notice their confidence has been knocked and the robot can help restore that”.
According to an article on the website Mdtmag ALIZ-E professor of Cognitive Systems and Robotics, Tony Belpaeme, says the experiment is not simply about gaining the children’s attention, but rather engaging with children in a way they can accept and providing them with useful information they can understand and be motivated by.
In order to test the components of the software, ALIZ-E teamed up with a hospital in Milan, which was willing to evaluate the prototypes with the help of hundreds of children between the ages of seven and 11, who each played with and learned from the ALIZ-E robot. Following their initial success trails were then carried out in 11 other centers across Europe.
ALIZ-E has given scientists researched insights on how children relate to social robots and how robots need to be designed to maximize their impact when used for educational or therapeutic purposes.
“The robot needs to personalise what it does. If it treats children on an individual level, they immediately relate to it, it taps into our primitive need to interact and communicate. One of the things that does appeal to children is that the robot make mistakes; if it never did so, it could become intimidating. It makes the child realise they too don’t have to be perfect all of the time,” says Belpaeme.
Through the course of their project the team at ALIZ-E say they have discovered many surprising and noteworthy facts about their prototypes. For example they found that using quirky Star Wars R2D2 sounds made it easier to communicate emotions to children. They also found results were better using an actual robot for educational purposes, rather than a screen.
The team involved with the ALIZ-E project is now reaching their conclusion, while also exploring other uses for the robots. They believe the same developed during the project could be of beneficial use to children on the autistic spectrum.
“Our initial work shows it could have an incredibly positive impact on those children, and given that autism can impact heavily on someone’s ability to communicate and build relationships, we now need to establish why it seems they can relate to a tiny robot.
“From that, we can explore how widely we can use the robot as a therapeutic tool and can we, in fact, use it to teach about wider social interactions,” says Belpaeme.