How robots are helping children with autism

Tags

autism, body movements, chest monitor, Children, classroom, communication, early diagnosis, emotion, facial expressions, family, feedback, interaction, modes, motions, non-threatening, non-verbal communication, reactions, research, robot, social interaction, social skills, teacher, therapist, treatment, withdrawal

How robots are helping children with autism

Anthony Arceri is seven and has autism. His clothes are covered in sensors, and he is standing in front of Zeno, a smiling, 2ft-tall robot. “What is your favourite food?” Zeno asks Anthony. “Chocolate milk and french fries.” “I love chocolate milk,” Zeno replies. The robot raises its arm, and Anthony copies. Zeno rubs his stomach, and so does Anthony.

It looks like fun – and for Anthony, it is. But researchers believe the interaction between Anthony and the robot also holds the key to early diagnosis and treatment of autism. Zeno is the result of a collaboration between Dr Dan Popa at the University of Texas at Arlington, Hanson RoboKind, Dallas Autism Treatment Centre, Texas Instruments and National Instruments – and is the brainchild of Hanson Robot owner and former Disney imagineer David Hanson.

Diagnosis of child autism has traditionally taken place through social interaction and speech exercises. This means that, until a child can speak, diagnosis is either a lengthy process, or can’t happen. But Zeno can interact with children through nonverbal communication such as body movements and facial expressions, speeding up diagnosis and perhaps even enabling it to be carried out before a child can talk.

Zeno isn’t just used for diagnosis. Children with autism can sometimes find social interaction threatening – making them withdraw, even from family members. Robots such as Zeno have features that look slightly human, but are obviously not human. This makes communication, with all its complex and frightening subtleties and nuances, less complicated and more comfortable for the child.

Anthony’s mother, Pamela Rainville, found out about Zeno from the Dallas Autism Treatment Centre, and thought the project might benefit Anthony. “It’s always good for him to be put in different situations, things outside his normal routine. Anytime he can be around other people, it’s a good learning and growing experience for him.”

So far, Anthony has had two therapy sessions with Zeno. Rainville believes he got more out of the second meeting than the first, and she expects he will get even more out of subsequent interactions with the robot. “This second time, Anthony fist-bumped Zeno, which was great. It shows he was a little more relaxed.”

Popa believes that Zeno is a good motivator for children as he is engaging and non-threatening: the children listen to the robot. “The idea is for the robot to instruct kids, give them some useful social skills and at the same time observe their reactions and calculate their reaction times. That calculation could form some kind of an autism scale.”

He says there are three ways in which therapists can use Zeno. “The first mode is called a scripted mode of interaction, where you pre-programme a certain sequence of motions. For the second mode, we have added a control system so we can have an operator or therapist control the robot by tele-operations. In this mode, it mirrors the motions of the instructor.”

In the third mode, the child can take control of the robot. “This can be unsafe as the child can do things – such as slap himself – that the robot will copy and possibly break. So we tend to use this third mode as entertainment only.”

Zeno now has a brother, Milo, as well as an international family. Zeno came first, and is used in research and classroom settings. Milo was created specifically to work directly with children. According to Richard Margolin, director of engineering at Hanson RoboKind and part of the team who developed both robots, some children with autism who had never spoken directly to an adult teacher spoke to Milo.

Milo looks very similar to Zeno. His expressive face is an important feature, because a characteristic of autism is the inability to read and connect with the emotions of others. Children are asked to identify the emotion shown by Milo from multiple choices on an iPad. Milo’s eyes are cameras, recording feedback. The child wears a chest monitor that records changes in heart rate and therefore emotion. A typical lesson would involve Milo and a child interacting one-to-one; the child responding to the robot with an iPad, and a therapist or teacher present to help if needed and record difficulties and progress.

One of Zeno and Milo’s international relatives is Kaspar, designed in the UK by the University of Hertfordshire’s Adaptive Systems Research Group. The size of a small child, unlike Zeno and Milo, Kaspar has a neutral expression so that children can interpret him how they wish. Research is under way to see how Kaspar’s use could support children with other developmental conditions, such as Down’s syndrome or attention deficit hyperactivity disorder, known as ADHD.

Another distant cousin is Nao, who was created in 2006 by Aldebaran Robotics and is being developed as a “house robot”. Along the way, Nao has been used as an educational tool, and the University of Birmingham’s Autism Centre for Education and Research worked with Aldebaran Robotics on a version of Nao to help children with autism. But like Kaspar, Nao has an expressionless face.

What seems to be unique about Zeno and Milo is the way that their expressiveness defies long-held robotic conventions. Designed to be the first advanced social robots in the world, they could eventually have an impact far beyond the diagnosis and treatment of autism. RoboKind envisages a broader role for its robots in educating young children. In the words of his creators, Zeno represents the future of robotics and could be “a wonderful addition to every household”.