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 net robot controller with guaranteed tracking performance.

F L Lewis1, K Liu, A Yesildirek

  • 1Automation and Robotics Res. Inst., Texas Univ., Arlington, TX.

IEEE Transactions on Neural Networks
|January 1, 1995
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

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

Prognosis and treatment of pneumonia in children.

Archives of disease in childhood·2010
Same author

Pyloric Stenosis in Identical Twins.

British medical journal·2010
Same author

Reinforcement learning for partially observable dynamic processes: adaptive dynamic programming using measured output data.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2010
Same author

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

IEEE transactions on neural networks·2008
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

A novel neural network (NN) controller for robot arms ensures stable control and bounded weights. This approach enhances real-time performance by addressing reconstruction errors and disturbances in robot dynamics.

Area of Science:

  • Robotics
  • Control Systems
  • Artificial Intelligence

Background:

  • General serial-link robot arms require precise control for effective operation.
  • Traditional control methods can struggle with unknown disturbances and model inaccuracies.
  • Neural networks offer adaptive control capabilities but can face challenges with stability and weight boundedness.

Purpose of the Study:

  • To develop a robust neural network (NN) controller for general serial-link robot arms.
  • To ensure stable real-time tracking performance and bounded NN weights.
  • To address limitations of standard backpropagation in closed-loop robot control.

Main Methods:

  • A two-layer neural network controller structure is designed, maintaining linearity in parameters.

Related Experiment Videos

  • A filtered error/passivity approach is used to derive the NN controller, introducing new passivity properties.
  • Online weight tuning algorithms with a correction term and a robustifying signal are implemented.

    • Main Results:

    • The developed NN controller guarantees accurate tracking and bounded NN weights.
    • The controller structure allows for zero initialization of NN weights and online learning.
    • Analysis reveals conditions under which standard backpropagation can lead to unbounded NN weights.

    Conclusions:

    • The proposed NN controller provides a stable and effective solution for robot arm control.
    • The method enhances robustness against reconstruction errors and external disturbances.
    • This work contributes to the reliable application of neural networks in real-time robotic systems.