Computer Science Seminar Series

Abstract

Starting the recent years, a significant amount of effort has been dedicated to explore the potential of social signal processing in human interaction with embodied conversational agents and social robots. While there is a proliferation of studies that investigate specific aspects of embodied social interaction under laboratory conditions, hardly any attention has been paid to the design and realization of naturalistic social settings in which artificial agents autonomously interact with human users. To bring social agents to the people's daily environment, user-agent communication should be properly situated in the context of the application at hand rather than isolated as a laboratory experiment. In my talk, I will argue for a more integrated view of techniques for the realization of autonomous agents that interact with humans in naturalistic social settings. The talk will be illustrated by examples from various national and international projects in which we developed user interfaces that allow humans to interact with embodied conversational agents or social robots using speech, gestures, postures and facial expressions.

Bio

Elisabeth André is a Full professor of Computer Science at Augsburg University, and Chair of the Research Unit Human-Centered Multimedia. She has a long track record in multimodal interfaces, embodied conversational agents and social signal processing with more than 200 publications in these areas. She is Associate Editor of eight renowned journals including IEEE Transactions on Affective Computing, ACM Transactions on Interactive Intelligent Systems, and Member of the Editorial Board of the Journal of Autonomous Agents and Multi-Agent Systems. Furthermore, she is currently serving as the chair of the ERC (European Research Council) panel for Systems and Communication Engineering. In 2010, Elisabeth André was elected a member of the prestigious German Academy of Sciences Leopoldina, the Academy of Europe and AcademiaNet. She is also an ECCAI Fellow (European Coordinating Committee for Artificial Intelligence).

• Back to list