Socially-aware interfaces for supporting co-located interaction

Ambient intelligence refers to a vision of technology where physical environments are sensitive and responsive to people. One of the challenges to realize this vision is to leverage information available in the social context. My doctoral research focuses on how to design interfaces that support co-located multi-user interactions taking into account individual and group nonverbal behavior, such as proxemics, gaze direction and body movements. In particular, the research activities are twofold: to understand which nonverbal cues and social signals reflect engagement, cooperation and cohesion in co-located group activities and to design systems that can handle and manage this social information. I present an integrated research approach for designing multi-user interactions based on social signal processing and I discuss the progress-to-date toward the development of systems that can sense and respond to social context.