Integration of task-based exoskeleton with an assist-as-needed algorithm for patient-centered elbow rehabilitation
Delgado, Pablo Yihun, Yimesker S.
Delgado, Pablo
Yihun, Yimesker S.
Citations
Altmetric:
Authors
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2023-02-23
Type
Article
Genre
Keywords
Assist-as-needed,Exoskeleton,Robot-therapy,Rehabilitation
Subjects (LCSH)
Citation
Delgado, P.; Yihun, Y. Integration of Task-Based Exoskeleton with an Assist-as-Needed Algorithm for Patient-Centered Elbow Rehabilitation. Sensors 2023, 23, 2460. https://doi.org/10.3390/s23052460
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.
Table of Contents
Description
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Publisher
MDPI
Journal
Book Title
Series
Sensors
Volume 23, No. 5
Volume 23, No. 5
Digital Collection
Finding Aid URL
Use and Reproduction
Archival Collection
PubMed ID
DOI
ISSN
1424-8220