Friendly educational robot designed to help kids with autism

By Luke Dormehl Published September 19, 2016

Robots could be used to help kids diagnosed with autism spectrum disorder (ASD), according to a new research project carried out jointly by a university and a robotics startup.

Researchers at Spain’s Universidad Miguel Hernández and the Spanish Aisoy Robotics company are collaborating to investigate how the latter group’s pint-size educational Aisoy robot can enhance the effectiveness of therapy sessions at the UMH University Clinic — particularly related to developing children’s emotional, social, and cognitive skills.

Recommended Videos

As an example, the robot will express emotions a child can then identify, or suggest playing certain games. Over the course of their time together, the idea is that kids will build up emotional attachments with the robot, and the interaction will aid with therapeutic adherence.

1 of 5

robot could help kids with autism mg 1049 — Image used with permission by copyright holder

robot could help kids with autism mg 1029 copia — Image used with permission by copyright holder

robot could help kids with autism mg 1014 — Image used with permission by copyright holder

robot could help kids with autism mg 0955 copia 1 — Image used with permission by copyright holder

robot could help kids with autism mg 0850 — Image used with permission by copyright holder

“We already have an Emotional OS, called Airos, which includes an emotional engine, a cognitive engine, and a decision engine,” José Manuel del Río, Aisoy’s CEO, told Digital Trends. “It has an application level for building user apps, we call Bot-apps. Clinica Universitaria UMH and Aisoy [are working] together for designing and building Bot-apps which use Airos’ capabilities [as well as the] Aisoy1 robot, adapted to children with autism.”

Manuel del Río continued that the researchers have not yet carried out in-depth studies suggesting why robots — and the Aisoy robot in particular — are so well suited to this task, but his anecdotal experience suggests it has something to do with the “expressivity of the face” of the robot, which makes it easy for children to “understand and communicate with.”

Going forward, the goal is that the robot could also expand to help with other childhood problems, such as attention deficit disorder (ADD), hyperactivity and impulsivity symptoms.

“We are going to finish the development phase [of our current work] in a couple of weeks,” he said. “Then we are going to [start work on a] study applying that therapy [to] 50 children, [ranging between] 8 to 10 years old. If results are positive, we will deliver those programs to interested parents for [use in] their homes.”

The company hopes that a tested version of the autism software for the Aisoy robot will be available from January.

Former Contributor

I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…

Topics

Emerging Tech

Pangram, the gold standard for AI text checks, releases Image 1.0 tool to sniff fake pics and videos

It can identify AI-generated pictures with an astounding 99.96% accuracy on its own evaluation set.

AI image detector tool pangram

Pangram, one of the most widely used and trusted AI text detectors out there, is finally releasing its multimedia detection tools to the masses. Pangram Image 1.0, which was previously available as a research preview, is now widely available on the web, through the company’s API, and via its eponymous Chrome extension.

The company claims its image detector can identify AI-generated pictures with an astounding 99.96% accuracy on its own evaluation set. Pangram also notes that it has improved the model’s accuracy over the past few months, especially against edited images, low-resolution pictures, and pictures made by the most advanced AI models out there. As far as the competition goes, TruthScan achieves an accuracy of 96.33%, followed by AI or Not at 91.38% and Sightengine at 88.33%.

Emerging Tech

Scammers are using AI to fake missing pet photos, and what happens next is horrifying

Criminals are using AI-generated pet photos to convince desperate owners their missing animals have been found, before demanding money and making disturbing threats.

Brown and white cat meowing in Inzoi.

Losing a pet can be heartbreaking, and anyone who's experienced it knows how quickly you'd drop everything if someone called to say they'd found your missing dog or cat. Unfortunately, scammers have learned to exploit that desperation, and AI is making their tricks even more convincing.

A disturbing new scam is targeting pet owners across the UK, with criminals using AI-generated images to pretend they've found missing animals. They then demand money for their return, sometimes going as far as threatening to kill the pets if the owners refuse to pay. According to a BBC report, several pet owners have already experienced these attacks, with scammers using convincing photographs, emotional stories, and increasingly aggressive messages to pressure them into paying.

Emerging Tech

AI can turn your Instagram posts into scam that know a little too much about you

Your public social media posts could be helping scammers create emails that feel personal, and existing AI safeguards aren't doing enough to stop them.

Electronics, Mobile Phone, Phone

We've all received those suspicious emails claiming we've won something, missed a delivery, or need to urgently update our bank details. Most are easy enough to ignore, especially when they're full of strange wording or have absolutely nothing to do with us. But what happens when a scam email actually knows what you've been up to lately? That's where things get a little worrying.

Researchers at the University of Texas at Arlington have found that AI can use information people share publicly on social media to create phishing emails that feel personal. And we're not just talking about knowing your name or where you work. These emails can reference things you've recently done, places you've visited, or even something you've been looking forward to. The researchers showed how widely available AI models could gather these details and turn them into targeted messages, potentially letting scammers reach large numbers of people without spending hours researching each person individually.