A high-tech boost for education and health

In a Swiss classroom, two children try to get out of a twisted maze with the help of a cute little robot. Interaction is easy and fun. It also provides researchers with valuable insights into children’s learning process and the conditions under which information is most effectively assimilated.

Rapid improvements in intuitive human-computer interactions (HMIs) are expected to bring major changes to society. Two European research projects in particular shed light on how these trends could affect two key areas: education and health.

child learn

ANIMATAS, an EU-funded cross-border network of universities and industry partners, is investigating whether and how robots and artificial intelligence (AI) can help us learn more effectively. The concept revolves around making mistakes: children can learn by recognizing and correcting the mistakes of others. And getting a bot to make these mistakes can come in handy.

“A professor must not make mistakes,” said Mr. Mohamed Chetouani, professor at the Sorbonne University, Paris, and coordinator of the project. “But a robot, yes. And mistakes are very useful pedagogically.”

For Professor Chetouani, asking questions like “Can robots help children learn better” is fairly simple, as learning is a very complex concept. For example, according to him, the automatic assumption that children who are concentrated in the classroom learn more is not necessarily correct.

For this reason, from the beginning the project focused on asking more relevant and specific questions to determine how robots could be useful in the classroom.

ANIMATAS consists of sub-projects, each led by a researcher at the beginning of their career. One of the sub-projects aimed to better understand children’s learning process and to analyze the types of interactions that best help them retain information.

robot roles

An experiment conducted to answer this question invited children to team up with the robot QTRobot to find the best path on a map.

During the exercise, the robot interacts with the children and gives them advice and suggestions. It also carefully measures various indicators of children’s body language, such as eye contact and gaze direction, tone of voice and facial expression.

As they hoped, the researchers had confirmation that certain interaction patterns corresponded to enhanced learning. With this information, they can better assess the quality of children’s interactions with educational materials and develop long-term strategies to optimize these interactions and thereby maximize their learning potential.

The research team will then strive to find out how this improved learning through contact with the robot can be adapted for children with special educational needs.

“We think it could be very important in this context,” said Professor Chetouani.

help at hand

Aki Härmä, researcher at Philips Research Eindhoven, Netherlands, is convinced that robotics and AI will revolutionize healthcare.

In the project PhilHumanswhich he coordinates and is funded by the EU, early-stage researchers from five European universities are working with two commercial partners, R2M Solution in Spain and Philips Electronics in the Netherlands, to explore how innovative technologies can improve human health.

AI enables access to new services and “this means healthcare can be provided 24/7,” says Härmä.

He cites the immense potential that technology offers to help patients manage their own health from home: apps that can track a person’s physical and mental state and identify problems early, chatbots that provide advice and make diagnoses , and algorithms that allow robots to safely move around a home.

Empathic Bots

The project, which started in 2019 and will end in late 2023, consists of eight sub-projects, each led by a PhD student.

One of the sub-projects, led by Phillips researcher Rim Helaoui, is investigating how mental health professionals’ specific skills (like empathy and open-ended questioning) can be coded into an AI-powered chatbot. Such a capacity would allow people suffering from a mental disorder to receive support while staying at home and therefore at a lower cost.

The team quickly realized that replicating the full range of psychotherapeutic skills in a chatbot poses challenges that cannot all be solved at once. So she focused her efforts on a key problem: how to build an empathic bot.

“This is the essential first step in getting people to open up and trust each other,” explains Ms. Helaoui.

To start, the team created an algorithm capable of responding with the right intonation and delivering empathetic content. The technology has yet to be turned into an app or product, but provides a starting point that could be used in many different applications.

fast forward

PhilHumans is also exploring other avenues for applying AI to healthcare. An algorithm under development uses “camera vision” to understand the tasks a person is trying to perform and to analyze the environment.

The ultimate goal would be to use this algorithm in a home assistance robot to help people with cognitive problems with everyday tasks.

One of the factors driving the project, Härmä says, is how quickly other organizations are developing natural language processors with impressive capabilities like OpenAI’s GPT-3. The project wants to use this surprisingly rapid progress in this and other areas to make faster progress.

The ANIMATAS and PhilHumans projects are actively working to push the boundaries of intuitive MMI.

In doing so, they gave young researchers the opportunity to acquire valuable knowledge and make themselves known to companies in the industry. Thanks to these two projects, a new generation of highly qualified young researchers is well equipped to advance HMI and its potential applications.

Research for this article was funded by the EU’s Marie Skłodowska-Curie Actions (MSCA). This article was originally published inhorizonthe EU magazine for research and innovation.

To find out more about the EU-funded projects mentioned in this article, follow the links below.

ANIMATAS

PhilHumans

Leave a Comment