Call For Papers

IMITATION IN NATURAL & ARTIFICIAL SYSTEMS

Special Issue of the International Journal

CYBERNETICS AND SYSTEMS

published by

Taylor & Francis

edited by

Chrystopher L. Nehaniv and Kerstin Dautenhahn

*** Submissions due: 1 October 1999 ***


High quality journal submissions reporting original scientific work are invited for a special issue of the journal Cybernetics and Systems on the topic of Imitation in Natural and Artificial Systems.

Imitation is one of the most important mechanisms whereby knowledge can be transferred between agents (biological, computational or robotic autonomous systems). Both natural and artificial systems are of interest for this interdisciplinary area. The importance of imitation has grown increasingly in cognitive and social sciences, developmental psychology, animal behavior, artificial intelligence, robotics, programming by example (instructible agents), machine learning, user-interface design, cybernetics and systems, and other areas.

The areas of interest of the special issue include but are not limited to:

Imitation is believed to be among the least common and most complex forms of animal learning. It is found in highly social species which show, from a human observer point of view, 'intelligent' behavior and traits supporting the evolution of traditions and culture. Recently, imitation has begun to be studied in domains dealing with such non-natural agents as robots, and as a tool for easing the programming of complex tasks or endowing groups of robotic agents with the ability to share skills without the intervention of a programmer. Imitation plays an important role in the more general context of interaction and collaboration between agents and humans, e.g. between software agents and human users. Intelligent software agents need to get to know their users in order to assist them and do productive work on behalf of humans. Imitation is therefore a means of establishing a 'social relationship' and learning about the actions of the user, in order include them into an agent's own behavioral repertoire.

Imitation is on the one hand considered as an efficient mechanism of social learning. On the other hand, imitation methods as in programming by demonstration setups in robotics and machine learning have primarily focused on the technological dimensions, while disregarding the more social and developmental functions. Additionally, the split between imitation research in natural sciences and the sciences of the artificial has been difficult to bridge, as we lack a common framework supporting an interdisciplinary approach. Yet, studying imitation for an embodied system inhabiting a non-trivial environment leads one to address all major AI problems from a new perspective: perception-action coupling, body-schemata, learning of sequences of action, recognition and matching of movements, contextualization, reactive and cognitive aspects of behavior, the development of sociality, or the notion of `self', just to mention a few issues.

Imitation involves at least two agents sharing a context, allowing one agent to learn from the other. The exchange of skills, knowledge, and experience between natural agents cannot be achieved by brain-to-brain communication but is mediated via bodies, the environment, the verbal or non-verbal expression or body language of the `sender', which in return has to be interpreted and integrated in the `recipient's' own understanding and behavioral repertoire. Moreover, as imitation games between babies and parents show, the metaphor of `sender' and `receiver' is deceptive, since the game emerges from the engagement of both agents in the interaction (cf. notions of situated activity and interactive emergence). Thus, learning by imitation and learning to imitate are not just a specific topics in machine learning, but can be seen as a benchmark challenges for successful real-world AI Systems.

Following on the success of the recent symposium of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB) on Imitation in Animals and Artifacts, also organized by the editors of the special issue, the journal publication is expected to include, among other submissions, journal length extensions of some excellent papers presented at the symposium reporting original work meriting attention of the growing indisciplinary international community concerned with studies of imitation in natural and artificial systems. All submissions will be peer-reviewed.

Authors should adhere to the instructions for authors available on the Web at http://www.taylorandfrancis.com/authors/cbsauth.htm when submitting your first drafts for review. Suggested length of submissions is around 20-30 pages, adhering to the formatting instructions.

Authors are requested to inform the editors of the topic of a planned submission as soon as possible in advance of submission and to submit papers well before the deadline if possible in order to expedite the review process.


Important Dates:


How to submit:

Electronic submission is strongly encouraged:
Send a PostScript version of your article by electronic mail to C.L.Nehaniv@herts.ac.uk as an attachment, or compressed and uuencoded.

However, you may alternatively send three (3) hardcopies of your paper to:

Dr. C. L. Nehaniv (Cybernetics & Systems)
Interactive Systems Engineering
University of Hertfordshire
College Lane
Hatfield Herts AL10 9AB
United Kingdom
 Any questions concerning the appropriateness of planned submissions or other queries may be directed to the editors:
 
Chrystopher Nehaniv Kerstin Dautenhahn
University of Hertfordshire University of Reading
C.L.Nehaniv@herts.ac.uk K.Dautenhahn@reading.ac.uk