Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Intelligence with representation.

Luc Steels1

  • 1Sony Computer Science Laboratory, 6 rue Amyot, 75005 Paris, France. steels@arti.vub.ac.be

Philosophical Transactions. Series A, Mathematical, Physical, and Engineering Sciences
|November 6, 2003
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Reply to Boudry: The threat of evolvable AI is too grave to be left to intuition.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Evolvable AI: Threats of a new major transition in evolution.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

The evolutionary dynamics of language.

Bio Systems·2017
Same author

Human language is a culturally evolving system.

Psychonomic bulletin & review·2016
Same author

Agent-based models for the emergence and evolution of grammar.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2016
Same author

I'm gonna have to science the shit out of this: Comment on "Towards a Computational Comparative Neuroprimatology: Framing the language-ready brain" by Michael A. Arbib.

Physics of life reviews·2016
Same journal

Inverse FIP effect plasma in the solar atmosphere: a synthesis of current understanding and new insights from AR 11967.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

Signs of sulfur fractionation under high magnetic field strength.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

First ionization potential fractionation of sulfur observed with spectral imaging of the coronal environment.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

Chromospheric dynamics and turbulence regulate the solar FIP effect.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

Exploring the link between wave activity in the photospheric velocity driver and the FIP bias in the solar corona.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

Radiative hydrodynamic simulations of first ionization potential fractionation in solar flares.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
See all related articles

Behaviour-based robotics, inspired by cybernetics, achieves intelligence without symbolic AI representations. However, higher cognition requires situated, grounded representations developed through evolutionary language games in embodied agents.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Cognitive Science
  • Cybernetics

Background:

  • Behaviour-based robotics draws inspiration from early cybernetics, demonstrating intelligence without symbolic AI representations.
  • This approach highlights the potential for sensory-motor intelligence to emerge without complex internal models.

Purpose of the Study:

  • To investigate the necessity of representations for higher cognitive functions in artificial agents.
  • To propose a mechanism for developing situated, grounded representations in embodied agents.
  • To explore how evolutionary processes can shape these representations through interaction.

Main Methods:

  • The study proposes a scenario involving evolutionary language games.
  • Embodied agents participate in these games to develop communication and representation systems.

Related Experiment Videos

  • Agent interactions and environmental feedback drive the adaptation of representations.

    • Main Results:

    • The findings suggest that while not essential for basic sensory-motor tasks, representations become critical for advanced cognition.
    • Evolutionary language games facilitate the emergence of situated, grounded representations.
    • Agent-developed representations are shown to be adapted to specific needs and population conventions.

    Conclusions:

    • Higher levels of cognition in artificial systems necessitate the development of grounded representations.
    • Evolutionary language games offer a viable pathway for embodied agents to acquire such representations.
    • This work bridges behaviour-based approaches with the need for representational capabilities in AI.