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

Indirect iterative learning control for a discrete visual servo without a camera-robot model.

Ping Jiang1, Leon C A Bamforth, Zuren Feng

  • 1Department of Computing, University of Bradford, Bradford BD7 1DP, UK. p.jiang@bradford.ac.uk

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|August 19, 2007
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

Extracellular histones are clinically relevant mediators in the pathogenesis of acute respiratory distress syndrome.

Respiratory research·2017
Same author

Size effects of lamellar twins on the strength and deformation mechanisms of nanocrystalline hcp cobalt.

Scientific reports·2017
Same author

Comparative Evaluation of Background Subtraction Algorithms in Remote Scene Videos Captured by MWIR Sensors.

Sensors (Basel, Switzerland)·2017
Same author

The V-ATPase subunit A is essential for salt tolerance through participating in vacuolar Na<sup>+</sup> compartmentalization in Salicornia europaea.

Planta·2017
Same author

Hypo-fractionated SBRT for localized prostate cancer: a German bi-center single treatment group feasibility trial.

Radiation oncology (London, England)·2017
Same author

Reuse of Boron Waste as an Additive in Road Base Material.

Materials (Basel, Switzerland)·2017

This study introduces a novel discrete learning controller for robot trajectory imitation using vision, without needing a camera-robot model. It employs neural networks for accurate, adaptive control, overcoming singularity issues for precise movement replication.

Area of Science:

  • Robotics
  • Control Systems
  • Machine Learning

Background:

  • Robot trajectory imitation often requires precise camera-robot models.
  • Existing iterative learning control (ILC) methods struggle with unknown, time-varying system dynamics.

Purpose of the Study:

  • To develop a vision-guided robot trajectory imitation controller without prior camera-robot model knowledge.
  • To address the challenge of unknown and time-varying image Jacobian matrices in robot control.

Main Methods:

  • A discrete learning controller using neural networks to approximate the image Jacobian matrix.
  • An indirect iterative learning control (ILC) approach for adaptive weight identification.
  • A segmented training strategy and a weight modification algorithm to handle singularities and ensure invertibility.

Related Experiment Videos

Main Results:

  • The proposed controller successfully imitates robot trajectories through repetitive tracking.
  • Neural network approximation capability directly correlates with tracking accuracy.
  • The weight modification algorithm effectively circumvents singularity problems.

Conclusions:

  • The developed controller enables accurate robot trajectory imitation from visual demonstrations.
  • This method offers a robust solution for robotic systems with unknown, time-varying dynamics.
  • Validated through simulations and experiments, demonstrating practical applicability.