Ambient Intelligence in Edutainment: Tangible Interaction with Life-Like Exhibit Guides Alassane Ndiaye, Patrick Gebhard, Michael Kipp, Martin Klesen, Michael Schneider, Wolfgang Wahlster German Research Center for Artificial Intelligence DFKI GmbH, Stuhlsatzenhausweg 3, D-66123 Saarbrücken <first name>.<last name>@dfki.de Abstract. We present COHIBIT, an edutainment exhibit for theme parks in an ambient intelligence environment. It combines ultimate robustness and simplic- ity with creativity and fun. The visitors can use instrumented 3D puzzle pieces to assemble a car. The key idea of our edutainment framework is that all actions of a visitor are tracked and commented by two life-like guides. Visitors get the feeling that the anthropomorphic characters observe, follow and understand their actions and provide guidance and motivation for them. Our mixed-reality installation provides a tangible, (via the graspable car pieces), multimodal, (via the coordinated speech, gestures and body language of the virtual character team) and immersive (via the large-size projection of the life-like characters) experience for a single visitor or a group of visitors. The paper describes the context-aware behavior of the virtual guides, the domain modeling and context classification as well as the event recognition in the instrumented environment. 1 Introduction Ambient Intelligence (AmI) refers to instrumented environments that are sensitive and responsive to the presence of people. Edutainment installations in theme parks that are visited by millions of people with diverse backgrounds, interests, and skills must be easy to use, simple to experience, and robust to handle. We created COHIBIT (COnversational Helpers in an Immersive exhiBIt with a Tangible inter- face), an AmI environment as an edutainment exhibit for theme parks that combines ultimate robustness and simplicity with creativity and fun. The visitors find a set of instrumented 3D puzzle pieces serving as affordances. An affordance is a cue to act and since these pieces are easily identified as car parts, visitors are being motivated to assemble a car from the parts found in the exhibit space. The key idea of our edutain- ment framework is that all actions of a visitor, who is trying to assemble a car, are tracked and two life-like characters comment on the visitor’s activities. Visitors get the feeling that the anthropomorphic characters observe, follow and understand their actions and provide guidance and motivation for them. We have augmented the 3D puzzle pieces invisibly with passive RFID tags linking these items to digital representations of the same (cf. [9]). Since we infer particular assembly actions of the visitors indirectly from the change of location of the instru- In: Maybury, M., Stock, O., Wahlster, W. (eds.): Intelligent Technologies for Interactive Entertainment. Proceedings of the First International Conference, INTETAIN 2005, Madonna di Campiglio, Italy, November/December 2005. Series: Lecture Notes in Computer Science, Subseries: Lecture Notes in Artificial Intelligence, Vol. 3814, pp. 104-113, Springer, Berlin, Heidelberg, 2005.