Scientists have developed a system that enables a robot or computer avatar to help rehabilitate people suffering from social disorders such as schizophrenia or social phobia.

The computer avatar interacts with a patient while playing a version of the mirror game, in which two players try to copy each other’s motion whilst playing with coloured balls that can move horizontally on a string, researchers said.

b’Representational xc2xa0image | Source: Reuters’

It is easier to interact socially with someone who looks, behaves or moves like us, according to the researchers including those from the University of Bristol and University of Exeter in the UK.

Initially the avatar is like an alter ego, created to look and move like the patient to enhance their feelings of attachment.

Over time the avatar is slowly altered to become less similar, therefore helping with social rehabilitation.

The results show that players sharing similar movement features, or motor signature, interact and co-ordinate better.

b’Representational image | Source: Reuters’

This can be used for rehabilitation of patients with serious social disorders as an avatar can be created to act like an alter ego, programmed to look and move like the patient to enhance their feelings of attachment.

“It is very challenging to build an avatar that is intelligent enough to synchronize its motion with a human player, but our initial results are very exciting,” said Mario di Bernardo, Professor at the University of Bristol.

The research used the principles of dynamical systems and feedback control theory to embed the avatar with enough ‘intelligence’ to synchronize and respond to the motion of the human player.

The researchers, including those from University of Montpellier in France and University of Naples Federico II in Italy, now wish to build on the technology and set-up multiple human-machine interaction for social rehabilitation and make groups of people and avatars interact with each other to perform joint tasks together.

The research was published in the Journal of the Royal Society Interface.