acm-header
Sign In

Communications of the ACM

ACM TechNews

Robots That Monitor Emotions of Asd Children


View as: Print Mobile App Share:
Researcher attaches physiological sensors to study participant

John Russell

Vanderbilt University researchers have developed a system that enables robots to monitor a child's emotional state, potentially leading to robotic playmates that help autistic children learn social skills. Vanderbilt professor Nilanjan Sarkar says research has shown that children with autism spectrum disorder (ASD) are attracted to robots, supporting the idea that well-designed robots could become an important element in their treatment. However, he says that efforts have been limited because they have not had a way of monitoring the emotional state of the children, preventing the robot from responding automatically to their reactions.

Sarkar has developed a method that uses physiological measurements to monitor the emotional state of individuals. Sarkar and Vanderbilt professor Wendy Stone recently published the results of initial experiments in which six children with ASD between 13 and 16 years old were fitted with several physiological sensors and asked to play two games--the computer game Pong and a game of basketball in which the hoop and backboard were attached to a robotic arm. The experiments provided physiological data that can be used to develop mathematical models for each individual that predict their emotional state with an accuracy of 80 percent or better. The researchers also showed that this information can be used in real time to alter the game configuration to significantly increase the child's level of engagement.

From Exploration
View Full Article


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account