AAAI-2004 Workshop on
Anchoring Symbols to Sensor Data

Call for Papers
[ Focus | Objectives and topics | Format and attendance | Submission instructions | Important dates | Organizers ]

Extended submission deadline: March 19


The anchoring problem is an important aspect of the connection between symbolic and sensory based processes in autonomous robotic systems. Anchoring is the problem of how to create, and to maintain in time, the connection between the symbol- and the signal-level representations of the same physical object.

Anchoring must necessarily occur in any physically embedded system that comprises a symbolic reasoning component. One of the main difficulties with using symbolic representations for reasoning in embedded systems is how to link these representations to the real world. A typical example is the problem of connecting, inside an autonomous robot, the symbol used by a planner to refer to a particular room, say `room-21', to the vision or laser data that correspond to that specific room. This connection is necessary, among other things, to exploit linguistic knowledge provided by humans, e.g., regarding rooms and doors in a map. Another example is the problem of connecting the symbol used by a planner to refer to an object needed for an action, say `ball-1', to the data that correspond to that object in the sensori-motoric system. This connection must be dynamic since the same symbol must be associated to new entities in the perceptual stream in order to track the object over time or to re-acquire it at a later moment.

Anchoring must also occur in a multiple robot system, since the robots must agree about the meaning of the symbols used to refer to perceived objects in the environment. A typical example is the problem of establishing the correspondence between the symbols used by two different robots embedded in the same physical environment to refer to the same physical object, e.g., a room. We talk in this case of grounded communication. Grounded communication is also needed for efficient human-robot interaction.

Objectives and Topics

This workshop is the third event on this subject, and it will be devoted to assessing the progress toward the development of general theories and techniques for anchoring. In addition, this workshop will aim at making contact with other communities that address tasks in which anchoring is present even if it is not mentioned explicitly. Relevant communities include those which study cognitive vision, cognitive robotics, human-robot interaction, robot navigation and mapping, robot planning and execution, and cooperative robotics. Participants from related non-robotic communities, such as text and image classification, philosophy of language, and cognitive psychology, are also welcome.

Topics of interest to this workshop include, but are not limited to:

Format and Attendance

The workshop will include presentation of submitted papers, invited talks, a rump session, and joint discussions. The symposium will be of interest to researchers in artificial intelligence, robotics, intelligent control, and image processing, as well as those interested in cognitive psychology, ethology, philosophy, and linguistics.

The workshop is open to all interested people, but attendance is limited to active participants. Perspective authors should submit a full paper reporting original results. Submission of papers sumbitted to other conferences or workshops is possible, but the authors should explicitly indicate if this is the case. People who are interested in participating without presenting a paper are invited to submit a short statement of interest. The workshop proceedings will be published as a AAAI Technical Report.

Submission Instructions

Full papers should be typeset in single column, 10 or 11 point font, with at least 1 inch margins on all sides, and must be submitted as either a PS or a PDF file. Other, non-standard formats (eg, Word) cannot be accepted. Statements of interest can be submitted as a PS, PDF, or ASCII text file. Full papers must be 10 pages maximum. Statemes of interests are limited to two pages maximum.

Submissions should be made electronically by e-mail to (contact one of the chairs if you can not do that). In the body of the e-mail message, you must specify the following:

Paper title Name, affiliation, and email of all authors Name, email, and postal address of corresponding author Phone and fax of corresponding author Indicate if the paper has been submitted to another conference or workshop, and which one. Abstract (maximum 200 words)

All submissions will be acknowledged within a few days. Papers will be peer-reviewed and the decision of acceptance will be mailed to the corresponding author. Accepted papers will be included in the workshop notes and published as a AAAI Technical Report. They will also published in the workshop's web site. At least one author of each accepted paper must attend the workshop.

Important Dates

  March 19, 2004 Submissions due
  April 16, 2004 Notification of acceptance
  May 25, 2004 Camera ready papers due
  May 28, 2004 Registration due
-> July 26, 2004 Workshop day


Workshop Chairs

Silvia Coradeschi
Alessandro Saffiotti
  Dept of Technology, University of Örebro
Fakultetsgatan 1, S-70182 Örebro, Sweden
Tel: +46 (19) 30-3390
Fax: +46 (19) 30-3463

Program Committee

Antonio Chella   Univ. of Palermo, Italy
R. James Firby   I/NET Inc, MI, USA
Marcello Frixione   Univ. of Salerno, Italy
Frans C. A. Groen   Univ. of Amsterdam, The Netherlands
Ian Horswill   Northwestern University, IL, USA
Yves Lespérance   York University, Canada
Angel P. del Pobil   Univ. Jaume-I, Spain
Gerhard Sagerer   Univ. of Bielefeld, Germany
Stuart C. Shapiro   University at Buffalo, NY, USA
John K. Tsotsos   York University, Canada


[ Workshop Home ]

Website hosted by AASS
Last updated on June 17, 2004