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

Feedback error learning neural network for trans-femoral prosthesis.

V D Kalanovic1, D Popovic, N T Skaug

  • 1Department of Mechanical Engineering, South Dakota School of Mines and Technology, Rapid City 57701, USA.

IEEE Transactions on Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
|April 25, 2000
PubMed
Summary

Feedback-error learning (FEL) neural networks offer advanced control for powered trans-femoral prostheses. This hybrid approach simplifies prosthesis control by learning inverse dynamics, improving adaptability to walking perturbations.

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

Association between cardiac high-energy phosphate metabolism and whole body metabolism in healthy female adults.

Physiological research·2021
Same author

The implications of hypersomnia in the context of major depression: Results from a large, international, observational study.

European neuropsychopharmacology : the journal of the European College of Neuropsychopharmacology·2019
Same author

DIABETIC NEPHROPATHY IN PREGNANT WOMEN WITH TYPE 1 DIABETES (MULTIPLE CASES REVIEW AND DISCUSSION).

Georgian medical news·2018
Same author

Aggressiveness in depression: a neglected symptom possibly associated with bipolarity and mixed features.

Acta psychiatrica Scandinavica·2017
Same author

Polygenic risk has an impact on the structural plasticity of hippocampal subfields during aerobic exercise combined with cognitive remediation in multi-episode schizophrenia.

Translational psychiatry·2017
Same author

<i>PECAM-1</i> gene polymorphism (rs668) and subclinical markers of carotid atherosclerosis in patients with type 2 diabetes mellitus.

Balkan journal of medical genetics : BJMG·2016

Area of Science:

  • Biomedical Engineering
  • Robotics
  • Artificial Intelligence

Background:

  • Conventional control methods struggle with the complex, time-varying dynamics of powered trans-femoral prostheses.
  • Rule-based control systems exhibit limitations in adapting to external perturbations and environmental changes.

Purpose of the Study:

  • To develop and simulate a novel control strategy for powered trans-femoral prostheses using a Feedback-Error Learning (FEL) neural network.
  • To evaluate the FEL neural network's ability to identify prosthesis dynamics and enable adaptive trajectory tracking.

Main Methods:

  • Implementation of a FEL neural network, combining nonparametric identification with parametric modeling and control.
  • Simulation of a powered trans-femoral prosthesis under FEL control, including single joint movements and multijoint walking patterns.

Related Experiment Videos

  • Introduction of perturbations, such as ground reaction force changes and hip torque variations, to test controller robustness.

    • Main Results:

    • FEL successfully identified the inverse dynamics of a powered trans-femoral prosthesis during simulated joint movements.
    • The identified dynamics enabled the prosthesis to track desired walking trajectories within a multijoint structure.
    • The FEL controller demonstrated robust performance when subjected to external perturbations, maintaining correct leg motion.

    Conclusions:

    • FEL provides an effective hybrid control approach for powered trans-femoral prostheses, overcoming limitations of conventional methods.
    • This method eliminates the need for complex and time-consuming manual parameter identification.
    • FEL enhances prosthesis adaptability and responsiveness, crucial for naturalistic walking.