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

Robust neural-network control of rigid-link electrically driven robots.

C Kwan1, F L Lewis, D M Dawson

  • 1Intelligent Automation Incorporated, Rockville, MD 20850, USA.

IEEE Transactions on Neural Networks
|February 7, 2008
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

Estimation of the proportion of skin cancers attributable to occupational sun exposure in Reunion Island.

Annales de dermatologie et de venereologie·2025
Same author

H<sub>∞</sub> Static Output-Feedback Control Design for Discrete-Time Systems Using Reinforcement Learning.

IEEE transactions on neural networks and learning systems·2019
Same author

Editorial Special Issue on Deep Reinforcement Learning and Adaptive Dynamic Programming.

IEEE transactions on neural networks and learning systems·2018
Same author

Heterogeneity of information regarding inhibitors in the product monographs of antihaemophilic factors in North America.

Haemophilia : the official journal of the World Federation of Hemophilia·2015
Same author

A rare microscopic finding in an early abortion specimen.

Journal of postgraduate medicine·2014
Same author

Effects of intra-articular sodium pentosan polysulfate and glucosamine on the cytology, total protein concentration and viscosity of synovial fluid in horses.

Australian veterinary journal·2012
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a robust neural-network (NN) controller for rigid-link electrically driven (RLED) robots. The controller offers online tuning and guarantees stability without complex preliminary analysis, making it universally applicable.

Area of Science:

  • Robotics
  • Control Systems Engineering
  • Artificial Intelligence

Background:

  • Rigid-link electrically driven (RLED) robots require sophisticated control for precise motion.
  • Existing adaptive robot controllers often necessitate extensive preliminary analysis and regression matrix determination.
  • Neural networks (NNs) offer potential for approximating complex nonlinear functions in robotic systems.

Purpose of the Study:

  • To propose a robust neural-network (NN) controller for the motion control of RLED robots.
  • To develop an NN controller that avoids lengthy off-line learning phases.
  • To ensure guaranteed stability of tracking errors and NN weights.

Main Methods:

  • Utilized two-layer neural networks (NNs) to approximate complex nonlinear functions inherent in RLED robot dynamics.

Related Experiment Videos

  • Implemented an online tuning mechanism for NN weights, eliminating the need for offline training.
  • Developed a control strategy that guarantees uniformly ultimately bounded (UUB) stability for both tracking errors and NN weights.

    • Main Results:

    • The proposed NN controller successfully controls the motion of RLED robots.
    • Online tuning of NN weights was achieved without requiring an offline learning phase.
    • Uniformly ultimately bounded (UUB) stability of tracking errors and NN weights was mathematically guaranteed.
    • The controller eliminated the need for determining a regression matrix, simplifying the control design process.

    Conclusions:

    • The developed NN controller provides a robust and stable solution for RLED robot motion control.
    • The controller's universal applicability to any RLED robot without modification represents a significant advancement.
    • This approach simplifies adaptive control design by removing the requirement for extensive preliminary analysis.