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

Visually guided movements: learning with modular neural maps in robotics.

Jean Luc Buessler1, Jean Philippe Urban

  • 1TROP Research Group, University of Mulhouse, Mulhouse, France

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 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 journal

A practical design of backdoor trigger under frequency-based orthogonality constraints.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

EEG fine-grained visual semantic decoding via a multimodal framework.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Theoretical analysis of the denoising autoencoder using Tweedie's formula.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Frequency-based cross-attention fusion network for RGB-D salient object detection.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

HTNet: A self-supervised heterogeneous triple network for multi-modal data.

Neural networks : the official journal of the International Neural Network Society·2026

This study introduces a modular controller for robotics, inspired by biological learning. On-line adaptation of these modules in a visual servoing task yielded excellent results, demonstrating practical interest.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Computational Neuroscience

Background:

  • Robotics requires complex processing and modular controllers.
  • Adapting individual modules in connectionist systems is a significant challenge.
  • Biological learning offers insights into modular structures and decomposition.

Purpose of the Study:

  • To propose a novel approach for modular controller adaptation in robotics.
  • To leverage biological learning principles for system architecture.
  • To demonstrate the effectiveness of modular decomposition in robotic control.

Main Methods:

  • Developed a modular controller architecture inspired by biological systems.
  • Applied the approach to a robotic visual servoing task.

Related Experiment Videos

  • Implemented on-line, bi-directional learning algorithms for module adaptation.

    • Main Results:

    • Achieved excellent results with on-line adaptation of a simple, modular controller.
    • Demonstrated effective processing of multiple variables with limited memory.
    • Validated the approach through extensive computer simulations and robotic platform experiments.

    Conclusions:

    • The proposed modular decomposition and on-line adaptation approach is practically effective for robotic control.
    • Biological learning structures provide a viable model for designing adaptive robotic systems.
    • This method offers a promising solution for complex robotic processing challenges.