Expressive behaviour as a social signal for socially-competent human-robot interaction: Expre-ss

The travel grant would support work creating mechanisms for embodied social agents that apply theory of mind (ToM) capabilities to the detection and management by the agent of its own modelled affective state and the expressive behaviour it generates as a result. This will support the development of more socially competent agents suitable for a wider range of applications. It flows from work currently being conducted in the project SoCoRo (EP/N034546/1), investigating the use of an expressive robot to help high-functioning adults with autism with social signal processing.

Social agents are graphically or robotically embodied entities designed to act competently and successfully in everyday human social environments. These could be homes, schools, workplaces, or more public spaces, like shopping malls and museums. It is well-established that humans impute social agency to such embodied entities and therefore assume competence in the social signals humans use themselves to regulate interaction and to manifest what they feel or think. For this reason, researchers in embodied social agents have long worked on agent expressive behaviour - facial expressions, vocalisations, gestures, posture, both for graphical and robotic agents.

Generating expressive behaviour (as distinct from scripting via pre-annotated dialogue items) requires an architecture that can model affective responses. Such an architecture should be based on sound psychological theory, but should move beyond the rather simple idea that the social agent merely expresses its own internal state. A smile can mean very many things other than an internal state of happiness and an employee being dressed down by their boss is unlikely to express the anger they may feel. Social signals are social because they take into account the social context and the impact such signals may make on interaction partners. Social agents that motivate in education, offer support to the elderly, are involved in role-play, in training applications or in therapy all need this capability.The travel grant will support an investigation of generic mechanisms that can be implemented in existing social agent architectures.

The applicant will work with leading theorists at University of Geneva and then with the builders of the two leading agent architectures in University of Lisbon and University of Southern California.

Organisations applying embodied social agents in health, domestic support, training, education and therapy will benefit from the availability of more socially-competent embodied agents since these should both function more effectively, especially during long-term interaction, and be more acceptable to the humans with whom they interact.

This should support an increase in deployment into socially sensitive application domains with positive social impact on those interacting with such agents.

Companies manufacturing social robots will benefit from new mechanisms to generate appropriate expressive behaviour in their products.

Colleagues working in public engagement in robotics and dealing with some of the panic reactions generated by current hype will benefit from an example of socially useful robotics research.

Students of the HWU and University of Glasgow DTC will benefit from research-related teaching materials in their programmes.