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

Defining a neural network controller structure for a rubbertuator robot.

M Ozkan1, K Inoue, K Negishi

  • 1Bogaziçi University, Biomedical Engineering Institute, Istanbul, Turkey. mehmed@boun.edu.tr

Neural Networks : the Official Journal of the International Neural Network Society
|August 18, 2000
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

Ion channels on synaptic vesicle membranes studied by planar lipid bilayer method.

Biophysical journal·1992
Same author

Extracellular matrix formation in piecemeal necrosis: immunoelectron microscopic study.

Liver·1992
Same author

Roles of Ca2+ influx through ATP-activated channels in catecholamine release from pheochromocytoma PC12 cells.

Journal of neurophysiology·1992
Same author

Establishment of a folliculo-stellate-like cell line from a murine thyrotropic pituitary tumor.

Endocrinology·1992
Same author

An extract of Gymnema sylvestre leaves and purified gymnemic acid inhibits glucose-stimulated gastric inhibitory peptide secretion in rats.

The Journal of nutrition·1992
Same author

[Selection of methods for diagnosis and treatment of pancreatic cancer].

Gan to kagaku ryoho. Cancer & chemotherapy·1992
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a systematic method for controlling rubbertuator robot arms using backpropagation neural networks. This approach offers improved trajectory control accuracy compared to traditional PID controllers.

Area of Science:

  • Robotics
  • Control Systems
  • Artificial Intelligence

Background:

  • Rubbertuator robot arms are pneumatic, offering lightweight, high-power, compliant, and spark-free operation.
  • The inherent compressibility of air and elasticity of rubber introduce significant non-linearity and complexity in motion control.
  • Soft computing methods offer robust, low-cost solutions for non-linear industrial applications but often require fine-tuning of design parameters.

Purpose of the Study:

  • To propose a systematic method for defining the structure of a backpropagation neural network controller for rubbertuator robot systems.
  • To leverage the physical model of the robot to inform the neural network architecture.
  • To train the neural network to learn trajectory-independent parameters essential for robot dynamics.

Main Methods:

Related Experiment Videos

  • Developed a systematic approach to define the structure of a backpropagation neural network (BPNN).
  • Integrated the physical model of the rubbertuator robot into the neural network design.
  • Trained the BPNN to identify trajectory-independent dynamic parameters.

Main Results:

  • The proposed neural network controller demonstrated superior accuracy in trajectory control for rubbertuator robots.
  • Performance was quantitatively compared against a well-tuned Proportional-Integral-Derivative (PID) controller.
  • The BPNN approach proved more effective in managing the non-linear dynamics of the rubbertuator system.

Conclusions:

  • A systematic, model-based neural network structure definition enhances rubbertuator robot control.
  • This method provides a more accurate and robust alternative to traditional PID control for these compliant robots.
  • The approach effectively addresses the challenges posed by non-linearity in soft robotic systems.