Representations and Architectures for Cognitive Systems

Call for papers for a Special Issue on IEEE Transactions on Autonomous Mental Development

Guest editors:

·         Giorgio Metta, Italian Institute of Technology & University of Genoa, ITALY

·         Gordon Cheng, Technical University Munich, GERMANY

·         Tamim Asfour, University of Karlsruhe, GERMANY

·         Barbara Caputo, Idiap Research Institute, Martigny, SWITZERLAND

·         John K. Tsotsos, York University, CANADA

Forewords

The expected progress in machine learning and robotics shall enable tasks where robots have to have sophisticated cognitive skills. Unlike well-accepted computational models, advances in neuroscience suggest that the underlying “architecture” that yields such cognitive skills may not necessarily be the result of a single monolithic algorithm. Tantalizing results of neuroscience are elucidating the roles of different brain areas and their specific learning, sensorial and/or motor modality.

We can envisage architectures where multiple modes, actions, and learning components interact to achieve a given task. Examples exist in the domain of humanoid robotics, where one might like to learn about attention, reaching, grasping but also to select appropriate actions depending on the environmental and object affordances. Moreover, the discovery of suitable representations is fundamental to the success of these architectures.

In this enlarged view of cognitive systems, the almost forgotten concepts of active vision are revisited together with simultaneous sensory and motor, as well as multimodal learning. For example, in object categorization new methods are being developed that enable abstractions and effective representations, keeping into account the structure of object categories, their associated affordances and how embodiment, context and task affects modeling and learning for an autonomous agent.

This special issue of the Transactions of Autonomous Mental Development calls for papers in order to provide a snapshot of the state of the art in the development of artificial cognitive systems. One or more of the following topics (but not necessarily limited to) are welcome:

·         Architectures integrating communication, control and cognitive abilities

·         Combination of different learning modes (e.g. reinforcement learning, unsupervised learning)

·         Representations suitable for scalable cognitive architectures

·         Developmental components in system-level architectures

·         Attention and action selection

·         Cortical-like representations and computation

·         Tool use in task solving, understanding of affordances

·         Essential Computational building blocks supporting cognitive architectures

Important dates

·         Deadline for submissions: Feb 1st, 2010 March 1st, 2010 (EXTENDED)

·         Decision of the first round of review: April 15th, July 31st, 2010

·         Final decision: May 1st, Sept 15th, 2010

·         Camera ready: May 15th, Oct 1st, 2010

·         Electronic publication: May 25th, October, 2010

·         Printed version: July 10th, October, 2010

·         NOW PUBLISHED, Volume 2, ISSUE 4. For more information see: http://ieeexplore.ieee.org/xpl/tocresult.jsp?isnumber=5645770

Submission procedure

Two kinds of submissions are possible:

Regular papers, up to 15 double column pages;
Correspondence papers either presenting a "perspective" that includes insights into issues of wider scope than a regular paper but without being highly computational in style or presenting concise description of recent technical results, up to 8 double column pages.

Instructions for authors:

http://ieee-cis.org/pubs/tamd/authors/

We are accepting submissions through Manuscript Central at:

http://mc.manuscriptcentral.com/tamd-ieee (please select "Cognitive Systems" as the submission type)

When submitting your manuscript, please also cc to giorgio.metta (at) iit.it

More information

For more information, please contact Giorgio Metta at giorgio.metta (at) iit.it