Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Muscle Coordination and Action

Muscle Coordination and Action

Muscle coordination is a complex and finely tuned process essential for smooth and purposeful movements like flexion, extension, adduction, abduction, and rotation. The human body orchestrates the actions of various muscles working in concert, each with a specific role. Four functional types describe how muscles work together: agonist, antagonist, synergist, and fixator.
Agonists
Agonist muscles, often called prime movers, are the primary muscles responsible for producing a specific movement....

One-Degree-of-Freedom System

One-Degree-of-Freedom System

In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...

Excitation-Contraction Coupling in Skeletal Muscles

Excitation-Contraction Coupling in Skeletal Muscles

Excitation-contraction coupling is a series of events that occur between generating an action potential and initiating a muscle contraction. It occurs at the triad, a structure found in skeletal muscle fibers that comprise a T-tubule and terminal cisternae of the sarcoplasmic reticulum on each side. These triads are visible in longitudinally sectioned muscle fibers. They are typically located at the A-I junction — the junction between the A and I bands of the sarcomere.
When an action...

Kinematic Equations: Problem Solving

Kinematic Equations: Problem Solving

When analyzing one-dimensional motion with constant acceleration, the problem-solving strategy involves identifying the known quantities and choosing the appropriate kinematic equations to solve for the unknowns. Either one or two kinematic equations are needed to solve for the unknowns, depending on the known and unknown quantities. Generally, the number of equations required is the same as the number of unknown quantities in the given example. Two-body pursuit problems always require two...

Development of the Limb Synovial Joints

Development of the Limb Synovial Joints

Joints form during embryonic development in conjunction with the formation and growth of the associated bones. The embryonic tissue that gives rise to all bones, cartilage, and connective tissues of the body is called mesenchyme.
The mesenchymal stem cells differentiate into chondrocytes that form the hyaline cartilage, and later the cartilaginous model of the bone. This model further transforms into a bone. This process is known as endochondral ossification.
During development, the limbs...

You might also read

Related Articles

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

Sort by

Same author

More isn't always better: Too much exoskeleton torque can disrupt balance.

bioRxiv : the preprint server for biology·2026

Same author

Temperature and moisture management and mitigation techniques in prosthetic sockets and liners: A rapid review.

Prosthetics and orthotics international·2026

Same author

Deep domain adaptation eliminates costly data required for task-agnostic wearable robotic control.

Science robotics·2025

Same author

Dynamic Duo: Design and Validation of an Autonomous Frontal and Sagittal Actuating Hip Exoskeleton for Balance Modulation During Perturbed Locomotion.

IEEE robotics and automation letters·2025

Same author

A Deep Learning Framework for End-to-End Control of Powered Prostheses.

IEEE robotics and automation letters·2025

Same author

The case against machine vision for the control of wearable robotics: Challenges for commercial adoption.

Science robotics·2025

Search research articles

Related Experiment Video

Updated: Jun 7, 2025

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

Task-agnostic exoskeleton control via biological joint moment estimation.

Dean D Molinaro^1,2,3, Keaton L Scherpereel^4,5,6, Ethan B Schonhaut⁴

¹George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA, USA. molinarodean@gmail.com.

|November 13, 2024

Summary

This summary is machine-generated.

This study introduces a new task-agnostic controller for lower-limb exoskeletons, using a deep neural network to estimate joint moments. This enables coordinated assistance across diverse human activities, improving real-world exoskeleton viability.

More Related Videos

Development of a Novel Task-oriented Rehabilitation Program using a Bimanual Exoskeleton Robotic Hand

Development of a Novel Task-oriented Rehabilitation Program using a Bimanual Exoskeleton Robotic Hand

Published on: May 20, 2020

Experimental Methods to Study Human Postural Control

Experimental Methods to Study Human Postural Control

Published on: September 11, 2019

Related Experiment Videos

Last Updated: Jun 7, 2025

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

Development of a Novel Task-oriented Rehabilitation Program using a Bimanual Exoskeleton Robotic Hand

Development of a Novel Task-oriented Rehabilitation Program using a Bimanual Exoskeleton Robotic Hand

Published on: May 20, 2020

Experimental Methods to Study Human Postural Control

Experimental Methods to Study Human Postural Control

Published on: September 11, 2019

Area of Science:

Robotics
Biomechanics
Artificial Intelligence

Background:

Current lower-limb exoskeleton controllers struggle with diverse human movements, limiting their real-world application.
Existing systems often require task-specific tuning, hindering seamless transitions between activities.

Purpose of the Study:

To develop and evaluate a task-agnostic controller for lower-limb exoskeletons that assists users across a wide range of activities.
To enable autonomous, multi-joint assistance by estimating biological joint moments using a deep neural network.

Main Methods:

A deep neural network was trained to estimate hip and knee joint moments in real-time.
The controller was integrated into a clothing-integrated exoskeleton and tested during 28 different activities.
Performance was evaluated by comparing estimated moments to ground truth and assessing user energetics.

Main Results:

The controller accurately estimated hip and knee moments (average R² of 0.83) across 28 activities, from cyclic locomotion to unstructured tasks.
The task-agnostic controller significantly outperformed a task-classifier-based method.
User energetics were reduced by 5.3–19.7% across ten diverse activities without controller recalibration.

Conclusions:

A task-agnostic controller utilizing deep neural network-based moment estimation enables effective, coordinated assistance in lower-limb exoskeletons.
This approach significantly enhances exoskeleton adaptability and efficiency across a broad spectrum of human behaviors.
The developed controller is a crucial step towards the real-world viability of assistive exoskeletons.