"Robots are the Perfect Combination" to Treat Autism, New Study Suggests

Where adults have failed to engage children living with autism, robots are making progress.

by Josie Rhodes Cook

Robotics that engage kids with autism spectrum disorder can lead to improved interactions with adults, new research has found.

The development signals a potential aid to a condition that now affects one in 59 children in 11 states where it’s being monitored by the Centers for Disease Control. 

“Robots are the perfect combination,” says researcher Brian Scassellati, of Yale University. “They’re social enough to get people to respond to them. But they’re not too social that they provoke any kind of anxiety.”

The research, published Wednesday in the journal Science Robotics, used an autonomous robot for 30 days to increase social communication skills of 12 children aged 6 to 12. In the end, caregivers reported “improved social behavior directed both toward themselves and toward others, in areas including eye contact, initiation of communication, and responses to communication.”

The researchers, based at Yale University, also found that the kids showed marked improvement in joint attention skills with adults, even after the treatment sessions had concluded.

This sort of technology can be “applied to a wide range of other challenges,” Scassellati tells Inverse.

“The children showed improved performance across the board,” Scassellati said in a statement released with the research. “This was more than we had hoped; not only did the children and parents still enjoy working with the robot after a month, but the children were showing improvements that persisted even when the robots were not around.”

This specific study proves that social robots may offer immense possibility for ASD interventions in particular.

Robot interaction with child with ASD, alongside a caregiver.

Scassellati et al., Sci. Robot. 3, eaat7544 (2018)

The study notes that kids and adults with ASD “often have difficulty in responding to social overtures, recognizing the emotional states of others from visual or auditory cues, and understanding the importance of gaze as a social cue.” This study set out to see if an autonomous, socially assistive robot could help with the social skills of children with ASD.

Afterward, caregivers noted “increased social skill performance between their child and themselves,” more eye contact on the last day of the sessions compared to the first day, and more attempts to initiate communication by the end of the month. They also noted “more frequent responses to communication bids from the caregiver” on the final day than the first day.

For this study, therapy was provided directly in homes, rather than a clinical or laboratory space. The “robot-assisted intervention” involved a 30-minute session every day for one month, and “involved triadic interactions among the social robot, the child, and the caregiver.”

The child had opportunities to interact and share experiences with the caregiver during the intervention, and the sessions reportedly included the robot telling a story to the participants, followed by three games, and finally, a caregiver survey in which the they commented on their observations of the child and robot.

Fourteen families with a child with ASD were enrolled in the study, though two withdrew. Five of the children with ASD involved were females, and seven were males.

The experimental set-up as identified in the paper.

Scassellati et al., Sci. Robot. 3, eaat7544 (2018)

In all, 127 hours of data was collected from the interaction between the kids, the robot, and their caregivers. The children played hundreds of games with the robots, and caregivers completed an on-screen survey right after each day’s intervention about how the kids interacted with caregivers during the previous 24 hours, about their interactions with other people, and generally about engagement.

And the results weren’t just seen in interactions with caregivers. The caregivers also reported increased social skill performance from their child with other people in regards to eye contact and communication.

“Our system demonstrated the possibility and potential of autonomous robot interventions for autism,” the authors wrote. “Our results also showed improvements of children’s joint attention in the absence of the robot, indicating that the children were able to demonstrate greater skill in the context of human interactions.”

Robot interaction with child with ASD, alongside a caregiver.

Scassellati et al., Sci. Robot. 3, eaat7544 (2018)

But Scassellati tells Inverse these robots could help with skills for kids who face other challenges besides ASD as well. “Students in my group have used robots sharing the same technology to teach sixth-graders about mathematics, third-graders about how to deal with bullies, 1st graders about nutrition, and even 6-12 month old deaf infants about sign language,” he says.

And children aren’t the only ones who could benefit. “We’re also seeing the technology applied to helping seniors remember their medication, adults who want to loose weight, and many other domains,” Scassellati tells Inverse.

The authors believe the results of this study offer evidence “illustrating possible transferable social skills beyond robot-mediated interactions,” which could be a game-changer for kids who struggle with social skills, such as children on the autism spectrum.

But if what Scassellati told Inverse is any indication, there’s an untold number of possibilities for this kind of robotic intervention for people of all ages, making the future of robot-human interactions and interventions very exciting indeed.

Related Tags