Why and How to Model Multi-Moda Interaction for a Mobile Robot Companion

Title	Why and How to Model Multi-Moda Interaction for a Mobile Robot Companion
Publication Type	Conference Paper
Year of Publication	2007
Authors	Li S, Wrede B
Conference Name	Technical Report of the AAAI Spring Symposium on Interaction Challenges for Intelligent Assistants
Abstract	Verbal and non-verbal interaction capabilities for robots are often studied isolated from each other in current research trend because they largely contribute to different aspects of interaction. For a robot companionthat needs to be both useful and social however, these capabilities have to be considered in a unified complex interactin context. In this paer we present two studies in such a context that clearly reveals the strengths and limitations of these modalities and advocate their comlementary benefits for human-robot interaction. motivated by this evidence we propose a powerful interaction framework which acounts for flexible multi-modality management in complex interactions. Incorporates verbal + non-verbal capabilities User studies - confoirm effectiveness Need to incorporate facial experession in future? Use of non-verbal means to reflect robot internal state (listening, puzzled, undertanding, person detected, not-detected etc.)

Posted by mickwalters on Thursday, 19 February, 2009 /

Photos

Download the Lirec app now and learn all about what the project's objectives and outcomes were over the course of 5 years of research.

Now on Android.

LIREC partner Queen Mary University developed a fun collision game with our robot FLASH/EMYS. Now on the App Store!

This film made by LIREC partner Queen Mary University of London made the official selection of the International Film Festival at CERN.

Download the free mobile app that allows children of all ages to learn how to compose music.

Try our multiplayer online game and interact with live Lirec game companions by clicking on the plant spirit companion below!

Loading tweets.