Enhancing social interactions using information technology

Social pathologies, including schizophrenia, autism and social phobia, are mainly characterised by difficulties in interacting with other people. This causes much suffering both for the person and those that surround them. A new project, that aims to improve social interactions, will develop and test an innovative rehabilitation method using humanoid robotics and virtual reality.

The collaborative European research team, including Dr Krasimira Tsaneva-Atanasova and Professor Mario di Bernardo from the Department of Engineering Mathematics at the University of Bristol, have been awarded €2.9 million by the European Commission for the three-year project, known as AlterEgo.

The project is rooted in a new transdisciplinary theory in movement neuroscience and cognitive science, the theory of similarity. This theory suggests that it is easier to socially interact with someone who looks like us. This resemblance can be morphological (form of an alterego), behavioural (his/her actions), or kinematic (the way he/she moves).

AlterEgo anticipates real-time manipulations of these similarity clues. The patient will be placed in interactive situations with a virtual agent. In the early stage of rehabilitation, the virtual agent, displayed on a screen, will be the alterego of the patient, which is more reassuring as it is similar.

In later stages, the patient will face a humanoid robot - the European iCub robot - or the clinician.  Changes in appearance and behaviour, during the interaction, will be introduced very gradually.  The researchers will test, over a period of six months, a new rehabilitation method reducing the interaction difficulties of these patients by the virtue of more or less socially neutral artificial agents.

Dr Krasimira Tsaneva-Atanasova, Reader in Applied Mathematics and one of the academics working on the project, said: "In Bristol, we will be developing reliable mathematical models, numerical algorithms and feedback control strategies that allow real-time adaptation of the coupled patient-avatar/robot dynamics.  These are crucial for assessing and improving the impaired social interaction through, and in, co-ordination tasks."

Provided by University of Bristol