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 Video

Updated: Jul 10, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
06:52

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

Vectorizing Human Gait: An Adaptive Kinematic Embedding for Monitoring and Intent Detection.

Lyndon Tang, Arash Arami

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |July 8, 2026
    PubMed
    Summary

    This study introduces a real-time method using hip and knee angles to understand user intentions for lower-limb exoskeleton gait rehabilitation. The technique accurately models joint movements and detects gait changes, improving rehabilitation effectiveness.

    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

    Effects of multiple motor point stimulation on knee joint torque compared with conventional functional electrical stimulation.

    Biomedical engineering online·2026
    Same author

    Hierarchical Coarse-to-Fine cGAN for Subtype-Specific Freezing of Gait Signal Generation.

    IEEE journal of biomedical and health informatics·2026
    Same author

    Coordinated human-exoskeleton locomotion emerges from regulating virtual energy.

    PloS one·2025
    Same author

    Human-exoskeleton interaction portrait.

    Journal of neuroengineering and rehabilitation·2024
    Same author

    Employing Deep Reinforcement Learning to Maximize Lower Limb Blood Flow Using Intermittent Pneumatic Compression.

    IEEE journal of biomedical and health informatics·2024
    Same author

    IMU-Based Real-Time Estimation of Gait Phase Using Multi-Resolution Neural Networks.

    Sensors (Basel, Switzerland)·2024

    Area of Science:

    • Biomechanics
    • Robotics
    • Rehabilitation Engineering

    Background:

    • Lower-limb exoskeletons require precise user-robot coordination for effective gait rehabilitation.
    • Current methods may struggle with real-time adaptation to user's intended movements.

    Purpose of the Study:

    • To develop and validate a real-time method for estimating user's intended gait motions from hip and knee kinematics.
    • To create a feature vector for classifying gait patterns and detecting deviations during exoskeleton-assisted walking.

    Main Methods:

    • A processing pipeline involving gait phase estimation, standardization, and recursive fitting of a von Mises basis function model to joint angles.
    • Utilizing hip and knee flexion angle feedback to generate a kinematic feature vector.
    • Evaluating the algorithm on 16 participants across diverse walking conditions.

    More Related Videos

    Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents
    04:37

    Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

    Published on: July 6, 2022

    Related Experiment Videos

    Last Updated: Jul 10, 2026

    Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
    06:52

    Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

    Published on: April 3, 2026

    Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents
    04:37

    Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

    Published on: July 6, 2022

    Main Results:

    • The von Mises basis model accurately reconstructs gait cycle kinematics (R² > 0.90 ± 0.03).
    • The derived feature vector effectively classifies different walking conditions and detects gait changes like limping.
    • The method provides real-time maximum likelihood estimates of joint kinematics, independent of the current gait phase.

    Conclusions:

    • The proposed real-time method accurately captures user's intended gait kinematics for lower-limb exoskeleton control.
    • This approach enhances the potential for adaptive and personalized gait rehabilitation by enabling efficient detection of gait variations.
    • The kinematic feature vector offers a robust representation for real-time gait analysis and control in exoskeleton applications.