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

Repeatability of Knee Kinematic Gait Outcomes Using a Novel Hospital Hallway Setup of a Markerless Motion Capture System.

Journal of applied biomechanics·2025
Same author

Clinically Relevant Gait Biomechanics Improvements After Total Knee Arthroplasty.

Journal of applied biomechanics·2025
Same author

High-Knee-Flexion Posture Recognition Using Multi-Dimensional Dynamic Time Warping on Inertial Sensor Data.

Sensors (Basel, Switzerland)·2025
Same author

AMBER: A Device for Hand Motor and Cognitive Rehabilitation-Development and Proof of Concept.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2024
Same author

On the Effect of Vibrotactile Stimulation in Essential Tremor.

Healthcare (Basel, Switzerland)·2024
Same author

Individualized Three-Dimensional Gait Pattern Generator for Lower Limbs Rehabilitation Robots.

IEEE ... International Conference on Rehabilitation Robotics : [proceedings]·2023

Related Experiment Video

Updated: Jun 23, 2025

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
06:54

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

14.1K

Novel Methods for Personalized Gait Assistance: Three-Dimensional Trajectory Prediction Based on Regression and LSTM

Pablo Romero-Sorozábal1, Gabriel Delgado-Oleas1,2, Annemarie F Laudanski3

  • 1BioRobotics, Centro de Automática y Robótica, Consejo Superior de Investigaciones Científicas-Universidad Politécnica de Madrid (CSIC-UPM), 28500 Madrid, Spain.

Biomimetics (Basel, Switzerland)
|June 26, 2024
PubMed
Summary

This study introduces advanced 3D gait trajectory prediction for robotic gait assistance. Personalized models improve human-robot interaction in rehabilitation by accurately mapping individual joint movements.

Keywords:
LSTMgait patternregressionrobotic gait support

More Related Videos

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.7K
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.2K

Related Experiment Videos

Last Updated: Jun 23, 2025

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
06:54

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

14.1K
3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.7K
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.2K

Area of Science:

  • Robotics
  • Biomechanics
  • Artificial Intelligence

Background:

  • Personalized gait assistance is key for effective human-robot interaction in rehabilitation.
  • Traditional Clinical Gait Analysis (CGA) lacks individual variability, limiting personalized gait trajectory generation.
  • Existing regression and Artificial Neural Network (ANN) models offer adaptable gait patterns but often focus on angular estimations.

Purpose of the Study:

  • To develop and validate a novel approach for predicting comprehensive 3D spatial gait trajectories (hip, knee, ankle) for personalized robotic gait assistance.
  • To enhance the accuracy and adaptability of gait pattern generators beyond angular estimations.
  • To improve the performance of end-effector rehabilitation robotic devices through individualized kinematic predictions.

Main Methods:

  • Utilized regression models and Long Short-Term Memory (LSTM) networks, a type of Artificial Neural Network (ANN).
  • Expanded ANN and regression applications to predict three-dimensional spatial trajectories, not just angular estimations.
  • Tailored gait trajectory predictions to individual subject kinematics.

Main Results:

  • The regression model achieved an overall Root Mean Square Error (RMSE) of 13.40 mm and a correlation coefficient of 0.92.
  • The Long Short-Term Memory (LSTM) model demonstrated state-of-the-art accuracy with an RMSE of 12.57 mm and a correlation of 0.99.
  • The developed models provide comprehensive spatial trajectories for hip, knee, and ankle joints, reflecting individual kinematics.

Conclusions:

  • The novel approach significantly enhances personalized gait trajectory assistance in robotic rehabilitation.
  • Accurate 3D spatial gait predictions improve human-robot interaction and the effectiveness of rehabilitation devices.
  • Advanced ANN and regression techniques show great potential for future personalized robotic gait assistance systems.