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

Neural network based control schemes for flexible-link manipulators: simulations and experiments.

H A. Talebi1, K Khorasani, R V. Patel

  • 1Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
PubMed
Summary

This study introduces novel neural network controllers for flexible-link manipulators, achieving precise tip position tracking without needing payload mass information. The developed controllers demonstrate effective performance through simulations and experiments.

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

Distributed reconfigurable control strategies for switching topology networked multi-agent systems.

ISA transactions·2017
Same author

An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines.

Neural networks : the official journal of the International Neural Network Society·2016
Same author

Hybrid fault diagnosis of nonlinear systems using neural parameter estimators.

Neural networks : the official journal of the International Neural Network Society·2013
Same author

Gene interaction networks based on kernel correlation metrics.

International journal of computational biology and drug design·2013
Same author

A recurrent neural-network-based sensor and actuator fault detection and isolation for nonlinear systems with application to the satellite's attitude control subsystem.

IEEE transactions on neural networks·2008
Same author

Application of adaptive constructive neural networks to image compression.

IEEE transactions on neural networks·2008

Area of Science:

  • Robotics
  • Control Systems Engineering
  • Artificial Intelligence

Background:

  • Flexible-link manipulators present control challenges due to their inherent dynamics.
  • Accurate tip position tracking is crucial for many robotic applications.
  • Existing control methods often require precise knowledge of system parameters, including payload mass.

Purpose of the Study:

  • To develop and evaluate novel neural network-based controllers for tip position tracking of flexible-link manipulators.
  • To investigate control schemes that minimize the need for a priori knowledge of system parameters, specifically payload mass.
  • To compare the performance of four distinct neural network control strategies.

Main Methods:

  • Utilized the modified output re-definition approach for controller design.

Related Experiment Videos

  • Proposed four neural network schemes, including two based on feedback-error-learning and two that relax assumptions about system models.
  • Employed online training for all neural networks, eliminating the need for offline training.

    • Main Results:

    • Demonstrated effective tip position tracking for flexible-link manipulators using the proposed neural network controllers.
    • Validated controller performance through simulation on a two-link planar flexible manipulator and experimental testing on a single flexible-link test-bed.
    • Showcased the capability of the controllers to operate without prior knowledge of the payload mass.

    Conclusions:

    • Neural network-based controllers, designed using the modified output re-definition approach, offer a viable solution for precise tip position tracking in flexible-link manipulators.
    • The proposed schemes effectively learn the inverse dynamics and adapt to system uncertainties, including unknown payload mass.
    • Online training of neural networks simplifies controller implementation and enhances adaptability in real-world robotic systems.