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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Task-Dependent Performance of Wearable Multimodal Biofeedback in Physical Rehabilitation: A Longitudinal Post-Stroke Case Study.

Healthcare (Basel, Switzerland)·2026
Same author

From Pixels to Patterns: A Multidimensional Framework to Decode Cytoskeletal Organization.

Computational and structural biotechnology journal·2026
Same author

Sublethal effects and bioaccumulation of "smart" anti-corrosion nanoadditives spiked in sediment in the ragworm Hediste diversicolor.

Aquatic toxicology (Amsterdam, Netherlands)·2026
Same author

Hereditary diffuse gastric cancer in progress: Comparative lessons from Lynch syndrome.

European journal of human genetics : EJHG·2025
Same author

The biomedical engineer's pledge: overview and context.

Medical & biological engineering & computing·2025
Same author

Functional Profile Differences Across Diagnostic Categories Using WHODAS 2.0 in Adults with Neurological, Musculoskeletal, and Chronic Pain Conditions.

Journal of functional morphology and kinesiology·2025

Related Experiment Video

Updated: Sep 3, 2025

Movement Retraining using Real-time Feedback of Performance
08:16

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

13.5K

Feedback-Error Learning for time-effective gait trajectory tracking in wearable exoskeletons.

Joana Figueiredo1,2, Pedro Nuno Fernandes1,2, Juan C Moreno3

  • 1Center for MicroElectroMechanical Systems (CMEMS), University of Minho, Guimarães, Portugal.

Anatomical Record (Hoboken, N.J. : 2007)
|July 23, 2022
PubMed
Summary

The Feedback-Error Learning (FEL) controller offers accurate and timely gait trajectory tracking for exoskeletons. This bioinspired control adapts to user needs and disturbances, outperforming traditional methods in rehabilitation.

Keywords:
Feedback-Error Learning controlbioinspired controllersexoskeletongait rehabilitation

More Related Videos

Training Persons with Spinal Cord Injury to Ambulate Using a Powered Exoskeleton
09:46

Training Persons with Spinal Cord Injury to Ambulate Using a Powered Exoskeleton

Published on: June 16, 2016

20.7K
A Method for Evaluating Timeliness and Accuracy of Volitional Motor Responses to Vibrotactile Stimuli
07:28

A Method for Evaluating Timeliness and Accuracy of Volitional Motor Responses to Vibrotactile Stimuli

Published on: August 2, 2016

7.3K

Related Experiment Videos

Last Updated: Sep 3, 2025

Movement Retraining using Real-time Feedback of Performance
08:16

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

13.5K
Training Persons with Spinal Cord Injury to Ambulate Using a Powered Exoskeleton
09:46

Training Persons with Spinal Cord Injury to Ambulate Using a Powered Exoskeleton

Published on: June 16, 2016

20.7K
A Method for Evaluating Timeliness and Accuracy of Volitional Motor Responses to Vibrotactile Stimuli
07:28

A Method for Evaluating Timeliness and Accuracy of Volitional Motor Responses to Vibrotactile Stimuli

Published on: August 2, 2016

7.3K

Area of Science:

  • Biomedical Engineering
  • Robotics
  • Rehabilitation Technology

Background:

  • Exoskeleton control requires user-oriented, adaptive responses for effective gait rehabilitation and human-robot interaction.
  • Existing controllers often struggle with dynamic changes and precise trajectory tracking during human-robot interaction.
  • A need exists for advanced control strategies that enhance the adaptability and efficiency of wearable exoskeletons.

Purpose of the Study:

  • To investigate the performance of a bioinspired hybrid Feedback-Error Learning (FEL) controller for exoskeleton gait rehabilitation.
  • To evaluate FEL's ability to achieve time-effective tracking of user-oriented gait trajectories and adapt to dynamic user interactions.
  • To benchmark FEL against conventional control methods, including Proportional-Integral-Derivative (PID) and lookup table feedforward with PID.

Main Methods:

  • Developed a hybrid FEL controller combining a PID feedback controller with a three-layer neural network feedforward controller.
  • The feedforward component learns the exoskeleton's inverse dynamics from real-time feedback commands.
  • Validated FEL with able-bodied subjects using knee and ankle exoskeletons during walking at various speeds and with induced gait disturbances.

Main Results:

  • FEL demonstrated high accuracy (tracking error <7%) and minimal delay (<30 ms) in tracking gait trajectories.
  • The feedforward controller effectively learned inverse dynamics and adapted to gait variations (speed, position range).
  • FEL significantly outperformed PID (error <27%, delay <260 ms) and PID with lookup table (error <17%, delay >160 ms) in accuracy and time-effectiveness.

Conclusions:

  • The Feedback-Error Learning (FEL) controller is a highly accurate and time-effective solution for exoskeleton gait rehabilitation.
  • FEL's adaptive capabilities and rapid learning make it suitable for real-time human-robot interaction in wearable systems.
  • The superior performance of FEL supports its application in repetitive gait training exoskeletons for enhanced clinical outcomes.