CTIT University of Twente
Research Business & Innovation About CTIT Research Calls Looking for a job? Intranet

25-26 April 2004: Lost in Ambient Intelligence


CHI 2004 Workshop, Vienna, Austria

Date and Venue:

April 25 or 26, 2004

See the official CHI 2004 website for recent information on dates, venue and registration: http://www.chi2004.org/


Anton Nijholt (CTIT-Twente, Netherlands)

Thomas Rist (DFKI, Germany)

Kees Tuinenbreijer (Philips, Netherlands)

Position paper deadline: January 12, 2004


Ambient intelligence environments will be integrated with our everyday environments. Garden, house, car, sitting room, study, office and in fact every environment and its natural objects allow perception of what is going on in the environment and allow interaction by its occupants and visitors to extract and exchange information (including moods and emotions).

Nevertheless, we should feel comfortable within them, although we know that the environment has eyes and ears that observe what we are doing. We should feel comfortable in addressing these environments when we need support. The environments will know about us. They know about our weak and strong points, maybe they will induce affiliation needs and attempt to induce self-disclosure since they can perform better when they know about our characteristics. We even have to assume that there is an audience in the 'background'. That is, there can be real-time involvement by those who own the environment or have been hired to provide user-support. Off-line processing (browsing of what has been going on or automatic detection and presentation of what is in the interest of those who control and maintain the environment) is another example of involvement the inhabitant may know about. In a home environment, we may assume that family members and friends can obtain access to such browsing facilities.

Most of the current research in ambient intelligence deals with how the environment is able to identify and model users' activities, rather than how the user is willing, able, or likes to communicate with the environment or have the environment communicate with him. In more traditional environments multimodality in interactions has received attention, but it has hardly been investigated how these results can be transferred to environments where the user does not always explicitly address a particular (part of a) screen or an object. Moreover, most of the research in ambient intelligence does not take into account that people may get lost in ambient intelligence, may not know who to 'talk' to and may not be able to build some kind of relationship with the anonymous environment that nevertheless supports them, observes them and keeps track of their activities.

Hence, an obvious question is, what kind of relationship do we have with our traditional human-computer interface. And, moreover, what kinds of relationships do HCI researchers want to establish between users and computers? And then, the next step is how does this translate to ambient intelligence environments. There is already a trend towards designing social interfaces, emphasizing human-to-human communication properties, rather than concentrating purely on designing intelligence and efficiency. In this research, the computer is perceived as a social actor, interaction should be socially formed and interaction design should take into account needs of emotions, personality, affiliation, friendship or even more.

We should mention that it is not unusual to contribute personality characteristics to a room, a house, a mall, a street or square, to a town or even to a landscape or another natural environment. Thoughts and activities (i.e., interactions with the environment) are influenced by a particular environment, but also, users or inhabitants may choose a particular environment, may adapt the environment to their preferences and, whatever they do, leave their traces and because of that, their personalities in these environments. There are links between individuals and the physical environments they occupy. Similarly, we may assume that whenever technology allows, consciously and unconsciously, links are created between individuals and their (ambient intelligence) environments. Which ones do we want to induce as HCI researchers?

For interface designers several questions arise. First of all, are there aspects of human-human interaction we do not want to loose because they allow or are necessary for social, private, efficient and entertaining human-environment interaction? Having identified these aspects, do we want or can we induce them when we design interaction between humans and environments? Which research questions have to be answered when we want to investigate social interaction, which research questions are there when considering private interactions, which research questions are there to consider when talking about efficient interaction, and which questions have to be answered when looking at problems or opportunities for entertaining interactions in ambient intelligence environments? More detailed questions can be asked, taking into account multi-disciplinary and mono-disciplinary viewpoints.

This workshop aims to:


Identify HCI problems related to interacting in ambient intelligence environments; shortcomings and necessary development of existing theories; role of the properties of the environment on interaction behavior of inhabitants, i.e., interacting with the environment and with other inhabitants. This includes issues as trust modeling, privacy awareness and presence. As such, it provides a forum to discuss the role of social psychology in ambient intelligence interaction.


Discuss the role of multi-party interaction modeling, assuming that objects, physical inhabitants, virtual inhabitants and (future) observers all play roles in the multi-party interaction. This research needs to take into account temporal and spatial characteristics of interaction in ambient intelligence environments, including cross-modal reference resolution.


Discuss problems related to the fusion and fission of information in ambient intelligence environments. Based on interpretation of information obtained from several sources it should be decided what actions should be taken by the environment and how they should be displayed. What is the state-of-the-art in multi-modal interaction modeling and does it cover the needs of ambient intelligence environments.

Participation and Submissions

We encourage participation from a wide range of disciplines including Human-Computer Interaction, Social Psychology, Computer Science, Artificial Intelligence and Natural Language Processing.

The workshop will be limited to 16 participants. Please submit a 2-4-page position paper outlining your interest in this topic to anijholt@cs.utwente.nl. Position papers must be received by 12 January 2004. Participants will be notified of selection by 23 February 2004.

The workshop format will include a presentation by each participant and discussion. In addition each participant will lead a discussion on the issues raised by another participant's paper.