Jove
Visualize
Contact Us

Related Experiment Videos

Is imitation learning the route to humanoid robots?

Schaal1

  • 1Department of Computer Science and Neuroscience, HNB-103, University of Southern California, Los Angeles, CA 90089-2520, USA.

Trends in Cognitive Sciences
|June 4, 1999
PubMed
Summary

This review explores how imitation learning in artificial intelligence can advance autonomous humanoid robots. Understanding motor control through imitation offers insights into creating more capable robots by bridging perception and action.

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

RAPD variation within and between natural populations of the wild rice oryza rufipogon from china and brazil

Heredity·1999
Same author

Constructive incremental learning from only local information

Neural computation·1998
See all related articles
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

Area of Science:

  • Artificial Intelligence
  • Neural Computation
  • Robotics
  • Neuroscience

Background:

  • Recent advancements in AI and neural computation focus on imitation learning and humanoid robot development.
  • Imitation learning is crucial for understanding perceptual motor control.
  • Research highlights the link between action and perception in motor control.

Purpose of the Study:

  • To investigate the role of imitation learning in advancing autonomous humanoid robots.
  • To explore how imitation learning provides insights into perceptual motor control mechanisms.
  • To review computational and biological approaches to imitation learning.

Main Methods:

  • Review of existing literature on imitation learning and humanoid robotics.

Related Experiment Videos

  • Analysis of research on action-perception connections and modular motor control.
  • Examination of computational models (AI, neural networks, statistical learning) and biological findings (primate brain activity).

    • Main Results:

    • Imitation learning addresses efficient motor learning, action-perception links, and modular control.
    • Primate brain research suggests a neural basis for imitation (shared areas for perception and execution).
    • Both traditional AI/robotics and modern neural network/statistical learning approaches are applied to imitation.

    Conclusions:

    • Imitation learning is a promising pathway for developing autonomous humanoid robots.
    • Understanding biological imitation mechanisms can inform computational models.
    • Parallels and differences between biological and computational imitation are identified, guiding future projects.