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

Design and Measured Assessment of a MOS-Only, Capacitorless, Miniature 64-Channel Headstage Circuit for High-Density Surface Electromyography.

Sensors (Basel, Switzerland)·2026
Same author

Concurrent control of natural and robotic limbs through a tactile-encoded brain-computer interface.

Nature communications·2026
Same author

Spiking neural network decoders of finger forces from high-density intramuscular microelectrode arrays.

Nature communications·2026
Same author

A Roadmap to Navigate the Future of Neural Engineering.

Journal of neural engineering·2026
Same author

Author Correction: Implanted microelectrode arrays in reinnervated muscles allow separation of neural drives from transferred polyfunctional nerves.

Nature biomedical engineering·2026
Same author

The increase in time to task failure following endurance training is associated with adjustments in motor unit firing properties.

Journal of applied physiology (Bethesda, Md. : 1985)·2026

Related Experiment Video

Updated: Jan 9, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.0K

High-level locomotion intent estimation from electromyography and body posture.

Balint Karoly Hodossy1, Dario Farina1

  • 1Department of Bioengineering, Imperial College London, London, United Kingdom.

Journal of Neural Engineering
|December 4, 2025
PubMed
Summary

Researchers can now estimate a person's intended walking path using muscle signals and body posture. This high-level (HL) intent estimation can improve wearable robotic devices and virtual environments.

Keywords:
AI and machine learningconvolutional networkselectromyographyhuman-machine interfacingintent estimationphysics-informed machine learning

More Related Videos

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.8K
Experimental Methods to Study Human Postural Control
08:12

Experimental Methods to Study Human Postural Control

Published on: September 11, 2019

10.0K

Related Experiment Videos

Last Updated: Jan 9, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.0K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.8K
Experimental Methods to Study Human Postural Control
08:12

Experimental Methods to Study Human Postural Control

Published on: September 11, 2019

10.0K

Area of Science:

  • Robotics
  • Biomechanics
  • Human-Computer Interaction

Background:

  • Walking becomes an automatic process once learned, requiring minimal conscious effort for low-level muscle control.
  • High-level (HL) user intent, such as desired path and pace, is key for seamless human-robot interaction with wearable devices.

Purpose of the Study:

  • To introduce a continuous representation of locomotion goals for estimating HL intent.
  • To investigate the estimation of horizontal walking paths from muscle signals and body posture data.

Main Methods:

  • Collected full-body motion capture and electromyography (EMG) data from 6 subjects during non-steady-state gait.
  • Trained temporal convolutional networks to predict walking paths causally, either directly or parametrically using a critically damped trajectory model.
  • Utilized a multimodal approach combining muscle and body posture signals.

Main Results:

  • Achieved a mean trajectory estimation accuracy of r²=0.89 for a 1-second walking path.
  • Successfully provided estimates for current and desired walking velocities, constrained by the walking path model.
  • Demonstrated the interpretability of the estimator's output.

Conclusions:

  • The developed approach enables subject-independent user interfacing for wearable robotic devices.
  • The HL intent representation is adaptable for use in virtual environments as a surrogate for biosignals.
  • This method offers a flexible and effective way to interpret human locomotion intent for robotic applications.