Journal article
Pablo Delgado, Yimesker Yihun
Italian National Conference on Sensors, 2023
Italian National Conference on Sensors, 2023
Semantic Scholar
DBLP
DOI
PubMedCentral
PubMed
Cite
Cite
APA
Click to copy
Delgado, P., & Yihun, Y. (2023). Integration of Task-Based Exoskeleton with an Assist-as-Needed Algorithm for Patient-Centered Elbow Rehabilitation. Italian National Conference on Sensors.
Chicago/Turabian
Click to copy
Delgado, Pablo, and Yimesker Yihun. “Integration of Task-Based Exoskeleton with an Assist-as-Needed Algorithm for Patient-Centered Elbow Rehabilitation.” Italian National Conference on Sensors (2023).
MLA
Click to copy
Delgado, Pablo, and Yimesker Yihun. “Integration of Task-Based Exoskeleton with an Assist-as-Needed Algorithm for Patient-Centered Elbow Rehabilitation.” Italian National Conference on Sensors, 2023.
BibTeX Click to copy
@article{pablo2023a,
title = {Integration of Task-Based Exoskeleton with an Assist-as-Needed Algorithm for Patient-Centered Elbow Rehabilitation},
year = {2023},
journal = {Italian National Conference on Sensors},
author = {Delgado, Pablo and Yihun, Yimesker}
}
Abstract
This research presents an Assist-as-Needed (AAN) Algorithm for controlling a bio-inspired exoskeleton, specifically designed to aid in elbow-rehabilitation exercises. The algorithm is based on a Force Sensitive Resistor (FSR) Sensor and utilizes machine-learning algorithms that are personalized to each patient, allowing them to complete the exercise by themselves whenever possible. The system was tested on five participants, including four with Spinal Cord Injury and one with Duchenne Muscular Dystrophy, with an accuracy of 91.22%. In addition to monitoring the elbow range of motion, the system uses Electromyography signals from the biceps to provide patients with real-time feedback on their progress, which can serve as a motivator to complete the therapy sessions. The study has two main contributions: (1) providing patients with real-time, visual feedback on their progress by combining range of motion and FSR data to quantify disability levels, and (2) developing an assist-as-needed algorithm for rehabilitative support of robotic/exoskeleton devices.