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

You might also read

Related Articles

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

Sort by

Same author

U<b>se of benzodiazepines and medications for opioid use disorder for withdrawal management in a hospital-based setting for individuals exposed to benzodiazepine-contaminated fentanyl: A case serie</b>s.

Drug and alcohol dependence reports·2026

Same author

Point-of-care ultrasound in Canadian anesthesiology residency programs: a follow-up survey.

Canadian journal of anaesthesia = Journal canadien d'anesthesie·2026

Same author

Physically Informed 3D Food Reconstruction: Methods and Results.

IEEE journal of biomedical and health informatics·2026

Same author

Human Papillomavirus Self-Sampling Attitudes Amongst Women Living with HIV Prior to a Self-Sampling Intervention.

Cancers·2026

Same author

Expanded CD16<sup>+</sup>CD56<sup>+</sup>Granzyme B<sup>+</sup> NK like CD8<sup>+</sup> T cells an off target effect of bruton's tyrosine kinase inhibitors in Waldenström macroglobulinemia.

Scientific reports·2025

Same author

Examining a Stabilization Center for Patients with Alcohol or Opioid Intoxication Transported by Paramedics: A Cohort Study of an Emergency Department Diversion Model.

Prehospital emergency care·2025

Same journal

DSPE-ViT: a lightweight vision transformer with dynamic sparse positional encoding for dense small object detection in UAV imagery.

Frontiers in neurorobotics·2026

Same journal

ST-HONet: Spatio-Temporal Hierarchical Network for long-horizon bimanual visuomotor imitation.

Frontiers in neurorobotics·2026

Same journal

ST-HADP: Spatio-Temporal hierarchical attention diffusion policy for long-horizon generalizable bimanual visuomotor imitation.

Frontiers in neurorobotics·2026

Same journal

EQISP: efficient quantized image signal processing with multi-scale pyramid fusion for resource constrained embodied perception.

Frontiers in neurorobotics·2026

Same journal

Research on embodied agent multimodal perception and real-time path planning algorithms for complex unstructured environments.

Frontiers in neurorobotics·2026

Same journal

NL-YOLOv5: a model with a larger receptive field and the ability to globally acquire features.

Frontiers in neurorobotics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 3, 2025

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Published on: July 22, 2014

Environment Classification for Robotic Leg Prostheses and Exoskeletons Using Deep Convolutional Neural Networks.

Brokoslaw Laschowski^1,2, William McNally^1,2, Alexander Wong^1,2

¹Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada.

Frontiers in Neurorobotics

|February 21, 2022

Summary

This summary is machine-generated.

Computer vision and deep learning predict walking environments for robotic prostheses. This system enhances control by anticipating conditions, improving safety and performance for users with mobility impairments.

Keywords:

artificial intelligence biomechatronics computer vision deep learning exoskeletons prosthetics rehabilitation robotics wearables

More Related Videos

The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals

The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals

Published on: January 13, 2022

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

Related Experiment Videos

Last Updated: Oct 3, 2025

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Published on: July 22, 2014

The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals

The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals

Published on: January 13, 2022

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

Area of Science:

Robotics
Computer Vision
Machine Learning

Background:

Robotic leg prostheses and exoskeletons offer mobility assistance.
Current control systems lack predictive capabilities due to sensor limitations.

Purpose of the Study:

Develop a computer vision-based environment classification system.
Enhance high-level control for robotic leg prostheses and exoskeletons.

Main Methods:

Created the ExoNet database: a large, diverse dataset of wearable camera images.
Trained and benchmarked deep convolutional neural networks (CNNs) on ExoNet.
Evaluated CNNs using NetScore, balancing accuracy and computational efficiency.

Main Results:

EfficientNetB0 achieved the highest test accuracy.
VGG16 demonstrated the fastest inference time.
MobileNetV2 offered the best NetScore, indicating optimal performance for real-time applications.

Conclusions:

Vision-based environment classification significantly improves robotic locomotion control.
The ExoNet database and benchmark provide a valuable resource for future research.
Optimizing CNN architecture selection is crucial for effective real-time robotic systems.