Assistive Robots and ASD

On September 25th a seminar was held at the University of Hong Kong by Professor Rajiv Khosla. Khosla works as part of Melbourne’s Research Center for Computers, Communication and Social Innovation (RECCSI). The topic of this seminar was how socially assistive robots can be of benefit to individuals diagnosed with Autism Spectrum Disorder (ASD). In Professor Khosla’s study, the socially assistive robot ‘Lucy’ was found to improve interaction skills and reciprocity in two Australian individuals with ASD, while reducing their required care time. Further details of the study can be found here.


If you are the parent of a child with ASD you may be aware of results like this emerging as part of a growing body of research related to assistive robots. You might also have quite a lot of questions: What are the implications for the average parents? Why would robots be used for this purpose? For parents of children with ASD these findings mean that a new avenue of therapy may be available for your child in the near future. It is possible that robots may be utilized by your child's teacher or therapist in the way that other technologies, such as tablet computers and software programs, currently are. 


Research has indicated that some individuals with ASD demonstrate a clear preference for technological, as opposed to human, interaction (Bekele et al., 2014). Children have been found to demonstrate better shared attention (eye contact, physical proximity, etc.) and facial expression imitation when paired with robots instead of humans (Duquette, Mercier & Michaud, 2006). This may be because humanoid robots appear similar to people, yet lack the complex facial expressions, vocal tones and unpredictability that individuals with ASD often find overwhelming. Socially assistive robots consistently perform repetitive activities, creating a safe, predictable environment for children with ASD (Boccanfuso & O’Kane, 2010).


Over the summer, I was privileged to participate in research at the Chinese University of Hong Kong with Professor So Wing Chee of the Department of Educational Psychology. Professor So’s study examines the effect of the robot NAO on improving nonverbal (i.e. gestural) communication in children with severe ASD. One of Professor So’s primary aims in conducting this research is to reduce the stress experienced by parents of children with ASD who are often unable to easily communicate with their children. Additionally, in a field dominated by English-language studies, Professor So’s work is one of few to address a Cantonese-speaking population. Her findings, to be released next year, will form an important addition to this area of study.


Inevitably, there are some limitations to the use of socially assistive robots. While working with Professor So, we observed that some of the gestures NAO produced were not identical to the typical human gesture, given NAO’s structural limitations; the robot has three instead of five fingers, and limited joint mobility. Moreover, acquisition of NAO or any other socially assistive robot comes at a high price. Nevertheless, it will be very interesting to monitor the coming developments in this research area. Please do not hesitate to approach me with any questions about this topic.





Bekele, E., Crittendon, J.A., Swanson, A., Sarkar, N., & Warren, Z. E. (2014) ‘Pilot clinical application of an adaptive robot system for young children with autism’, Autism, 18 (5), 598-608.


Boccanfuso, L., & O’Kane, J. M. (2010) ‘Adaptive robot design with hand and face tracking for use in autism therapy’, Proceedings of the 2nd International Conference on Social Robotics, Singapore.


Duquette, A., Mercier, H., & Michaud, F. (2006) ‘Investigating the use of a mobile robotic toy as an imitation agent for children with autism’, Proceedings of International Conference on Epigenetic Robotics: Modelling Cognitive Development in Robotic Systems, Paris.