As promised our research on AI and Autism continues and some amazing developments are going on across the globe.
Becky Ham ( MIT Media Lab ) reports on how personalised ” deep Learning ” equips robots for autism therapy .
This cutting-edge research is developing a system that allows autism therapy robots to help teach children how to decipher different emotions
“Children with autism spectrum conditions often have trouble recognising the emotional states of people around them – distinguishing a happy face from a sad one for instance.
To deal with this therapists are using kid-friendly robots to demonstrate those emotions and to engage the children in imitating the emotions and responding to them in appropriates ways.”
According to Becky researchers at the MIT Lab have now developed a type of personalised machine learning that helps robots estimate the engagement and interest of each child during these interactions ,using data that are unique to each child.
Armed with this personalised ” deep learning ” network the robots’ perception of the children’s responses agreed with assessments by human experts with a correlation score of 60% .
The correlation score are usually 50 to 60 % and the scientists are suggesting that robots that are trained on human observations, as in this study, could someday provide more consistent estimates of these behaviours .
The long -term goal is not to create robots that will replace human therapists ,but to augment them with key information that the therapist can use to personalise the therapy content and also to make more encouraging and naturalistic interactions between the robots and children with autism ” explains Oggi Rudovic ,a postdoc at the Media Lab and first author of this study.
The MIT research team realised that a kind of machine learning called deep learning would be useful for the therapy robots to have, to perceive the children’s behaviour more naturally .
For more information on these developments check it out at the Massachusetts Institute of Technology ( new.mit.edu )