Due to numerous requests, we are extending the deadline for the Intelligent Environments Symposium. Also, please see the listing below for sample submission topics.

Intelligent Environments are spaces in which computation is seamlessly used to enhance ordinary activity. They enable tasks historically outside the normal range of human-computer interaction by connecting computers to normal, everyday phenomena that have traditionally been outside the purview of contemporary user-interfaces. Their applications are not spreadsheets and word processing but intelligent rooms and personal assistants.

Interaction with these environments should be in terms of forms that people are naturally comfortable with. Their user-interface primitives are not menus, mice and windows but gesture, speech, context, and affect. At least in theory, it should be possible for a person to forget she is using a computer while interacting with one.

Building Intelligent Environments requires a unique breadth of knowledge that extends beyond any of the traditional boundaries of AI research areas. The purpose of this symposium is to bring together researchers from various AI backgrounds to discuss the issues involved in creating these complex, interactive, embedded systems. We expect to have relevant contributions from interested researchers in computer vision, software agents, knowledge representation, robotics, machine learning, and speech understanding.

Submissions need not deal explicitly with preexisting intelligent environments. We are very interested in submissions covering subsystems that would be useful components of these environments. Possible topics include:

Multimodal user-interfaces

Speech recognition and understanding systems

Software architectures for modular systems

Computer vision systems for gesture, face, and object recognition

Computer vision systems for people tracking

Audio systems for sound localization

Knowledge representation of real-world events

Application areas for intelligent environments

Submission Information:

Potential participants should submit a short paper (up to 5-8 pages) by October 24, 1997 describing work in progress, completed work, positions, testbeds, discussion topics or potential panels. Other interested participants should submit a one to two page description of their work or interest in this area (including a short list of related publications) or specific questions and issues that they feel should be addressed. Five hardcopies of your submission should be sent to:

Michael Coen

MIT AI Lab

545 Technology Square

Cambridge, MA 02139

(617) 253 8916

Submissions must include title, author’s name(s), affiliation, mailing address, e-mail address, phone and fax numbers. Invited participants will be asked to submit Postscript versions of their papers.

Organizing Committee: