Full-text

URL: http://www.cyber.rdg.ac.uk/people//people/kd/WWW/ABJ2.ps

Cached: PDF-435K    PS-786K    PS.gz-164K

SAVE AS an easy-to-recall long filename:

Filename format: author--year--title   PDF-435K    PS-164K    :: About GZip'd PS

Filename format: author--year--title--journal|proceedings|...--pages   PDF-435K    PS-164K

Related links

CiteSeer: http://citeseer.ist.psu.edu/billard99experiments.html

Web search: Google Web Search   ::   Google Scholar

Within this site: Cited by (13)    References (57)

Paper at a Glance

Experiments in learning by imitation ­ Grounding and Use of
Communication in Robotic Agents
Aude Billard \Lambda , Kerstin Dautenhahn y
\Lambda Dept. of Artificial Intelligence, U. of Edinburgh, 5 Forrest Hill, Edinburgh EH1 2QL
y Department of Cybernetics at the University of Reading
PO Box 225 Reading, RG6 6AY United Kingdom
audeb@dai.ed.ac.uk, K.Dautenhahn@cyber.reading.ac.uk
Contact:
Tel: +44­131­650­4491
Fax: +44­131­650­6899

Abstract Social behaviour and in particular social learning are key mechanisms for the cohesion and evolution of primate societies. Similarly, social skills might be desirable for artificial agents who are expected to interact with other natural or artificial agents. We view learning, communication and imitation as important capabilities to possess by social artificial agents and study how these skills can be designed and used by physically embodied autonomous robots. We study grounding and use of communication among heterogeneous agents. In particular, we investigate the role of social interactions for sharing of context and building of joint attention among communicative agents. Grounding and use of communication is investigated through simulations within a group of autonomous agents. Results show that social behaviour benefit the agents in two circumstances: (1) agents capable of following one another, and in this way imitating each other's
1  2 movements, develop faster and better a common understanding of the language; (2) furthermore, the agents' capability of communicating with one another via a common vocabulary benefits to the group and to each agent individually as it speeds up the transmission of information. We use a connectionist model, based on Hebbian associative learning, for the learning of the word­ signal pairs. This work follows robotic experiments [6, 5, 7] in which a physical autonomous robot was taught a vocabulary to describe its perceptions of objects, movement, inclination and orientation. The robot was taught ...

@article{billard99experimentsIn,
  author={A. Billard and K. Dautenhahn},
  title={Experiments in learning by imitation - grounding and use of communication in robotic agents},
  journal={Adaptive Behavior},
  year={1999},
  volume={7},
  number={3/4},
  pages={415-438},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/billard99experimentsIn.html}
}

HOME   ::  Journal List   ::   Article	Comments to: junwang4 you-know-at gmail.com	Last update: 10/27/09