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 payload estimation for adaptive robot control.

M R Leahy1, M A Johnson, S K Rogers

  • 1Air Force Inst. of Technol., Wright Patterson AFB, OH.

IEEE Transactions on Neural Networks
|January 1, 1991
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

Chronic erosive herpes simplex virus infection of the penis, a possible immune reconstitution disease.

HIV medicine·2001
Same author

Changing treatment patterns among patients with HIV: Royal Free Hospital 1987-97.

HIV medicine·2001
Same author

Oral and sub-cutaneous vaccination of commercial pigs with a recombinant porcine adenovirus expressing the classical swine fever virus gp55 gene.

Archives of virology·2001
Same author

Mitochondrial abnormalities in ageing macular photoreceptors.

Investigative ophthalmology & visual science·2001
Same author

Analysis of XRN orthologs by complementation of yeast mutants and localization of XRN-GFP fusion proteins.

Methods in enzymology·2001
Same author

Thalidomide is distributed into human semen after oral dosing.

Drug metabolism and disposition: the biological fate of chemicals·2001
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

Artificial neural networks improve robotic manipulator tracking accuracy by estimating payload variations. This adaptive control enhances robustness against dynamic uncertainties for better performance.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Control Systems

Background:

  • Robotic manipulator tracking accuracy is limited by dynamic interactions and payload uncertainties.
  • Model-based control algorithms require accurate dynamic models, which are often unavailable.
  • Existing methods struggle with real-time adaptation to changing payloads and modeling errors.

Purpose of the Study:

  • To propose and validate a concept for enhancing robotic manipulator high-speed tracking accuracy using artificial neural networks.
  • To develop a computationally efficient adaptive control strategy that addresses payload uncertainty and modeling errors.
  • To integrate neural network pattern recognition with model-based control for improved robustness.

Main Methods:

  • Utilized artificial neural networks (ANNs) for payload estimation by recognizing variations linked to tracking performance degradation.

Related Experiment Videos

  • Implemented a multilayer perceptron (MLP) architecture with two hidden layers for neural network payload estimation.
  • Combined ANN outputs with nominal dynamics knowledge to create a direct form of adaptive control.
  • Validated the concept through experimentation and analysis on a PUMA-560 manipulator.

    • Main Results:

    • Demonstrated that neural network payload estimation effectively recognizes payload variations.
    • Achieved enhanced tracking accuracy and robustness against incomplete dynamic information.
    • The proposed adaptive control strategy proved computationally efficient.
    • Experimental validation confirmed the efficacy of the integrated approach on a PUMA-560 manipulator.

    Conclusions:

    • Artificial neural networks offer a viable method for real-time payload estimation in robotic control.
    • The integration of ANNs with model-based control significantly enhances tracking robustness and accuracy.
    • The developed adaptive control algorithm is applicable to various robotic systems facing dynamic uncertainties.