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

Multilayer neural-net robot controller with guaranteed tracking performance.

F L Lewis1, A Yegildirek, K Liu

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

IEEE Transactions on Neural Networks
|January 1, 1996
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

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 author

Control of a nonholonomic mobile robot using neural networks.

IEEE transactions on neural networks·2008
Same author

Robust backstepping control of induction motors using neural networks.

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

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

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
Same journal

Data-based identification and control of nonlinear systems via piecewise affine approximation.

IEEE transactions on neural networks·2011
Same journal

Data-core-based fuzzy min-max neural network for pattern classification.

IEEE transactions on neural networks·2011
See all related articles

A novel neural-net (NN) controller for robot arms uses online tuning to ensure stable control. This approach guarantees bounded tracking errors without needing offline learning, improving robotic system performance.

Area of Science:

  • Robotics
  • Control Systems
  • Artificial Intelligence

Background:

  • Controlling general serial-link rigid robot arms presents challenges due to nonlinear dynamics and external disturbances.
  • Traditional control methods may struggle with the complexities of neural network (NN) based controllers, especially during online operation.
  • Existing backpropagation tuning methods are insufficient for robust closed-loop dynamic control in robotic applications.

Purpose of the Study:

  • To develop a multilayer neural-net (NN) controller for general serial-link rigid robot arms.
  • To introduce novel online weight tuning algorithms for NN controllers that ensure stability and performance.
  • To establish theoretical guarantees for bounded tracking errors and NN weights in dynamic robotic control.

Main Methods:

Related Experiment Videos

  • Derivation of the NN controller structure using a filtered error/passivity approach.
  • Development of novel online weight tuning algorithms, incorporating correction terms and a robust signal to the delta rule.
  • Analysis of NN properties, introducing concepts of passive, dissipative, and robust NNs.
  • Inclusion of a second-order forward-propagated wave in the backpropagation network for enhanced tuning.

Main Results:

  • The proposed NN controller does not require an offline learning phase and allows for easy weight initialization.
  • Guaranteed bounded tracking errors and bounded NN weights are achieved through the novel online tuning algorithms.
  • Specific bounds for tracking errors and NN weights are determined.
  • The tracking error bound can be made arbitrarily small by adjusting a feedback gain.

Conclusions:

  • The developed NN controller offers a robust and stable solution for controlling serial-link rigid robot arms.
  • The novel online tuning algorithms effectively address the limitations of standard backpropagation in dynamic control scenarios.
  • The introduction of passive, dissipative, and robust NN properties provides a new framework for analyzing and designing NN controllers.