Scientists develop 'deep learning' robots to empower & enable children with autism
July 1, 2018
It can often be quite challenging for therapists to engage with a child on the autism spectrum for even a few seconds. Now, they can look forward to some help from NAO, the deep thinking robot!
Scientists at the Massachusetts Institute of Technology in the United States have developed a new type of deep learning network that could work with robots and enable them to monitor the quality of their interactions with children with autism. It does by using data specific to each child.
Autism spectrum disorder is a condition related to brain development. It affects how a person perceives and socializes with others, leading to problems in social interaction and communication. The term spectrum refers to the wide range of symptoms and severity.
With the help of personalized deep learning, the child-friendly robot, called NAO can easily estimate the engagement and interest of each child, using data unique to that particular individual, based on a study performed on 35 children with autism.
The long-term goal is not to replace human therapists with robots, but to support them with key information that the therapists can use to personalize the therapy content. It will also help make interactions more natural and engaging.
The robot-assisted therapy involves a human therapist showing flash-cards of different faces expressing different emotions, like happiness, sadness and fear. A programmed robot or NAO then shows the same emotions to the child. The therapist observes how the child engages with the robot and gets feedback on how the lesson is to be taken further.
NAO is a two feet tall robot which looks like a armoured superhero. It conveys different emotions by changing its eye colour, limb-motion and the tone of its voice.