Design and Evaluation of a Soft Robotic Actuator with Non-Intrusive Vision-Based Bending Measurement

This paper presents the design and evaluation of a novel soft pneumatic actuator featuring two independent bending chambers, enabling independent joint actuation and localization for rehabilitation purposes. The actuator’s dual-chamber configuration provides flexibility for applications requiring cu...

Full description

Saved in:
Bibliographic Details
Main Authors: Narges Ghobadi, Witold Kinsner, Tony Szturm, Nariman Sepehri
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/13/3858
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850116224117112832
author Narges Ghobadi
Witold Kinsner
Tony Szturm
Nariman Sepehri
author_facet Narges Ghobadi
Witold Kinsner
Tony Szturm
Nariman Sepehri
author_sort Narges Ghobadi
collection DOAJ
description This paper presents the design and evaluation of a novel soft pneumatic actuator featuring two independent bending chambers, enabling independent joint actuation and localization for rehabilitation purposes. The actuator’s dual-chamber configuration provides flexibility for applications requiring customized bending profiles. To measure the bending angle of the finger joints in real time, a camera-based system is employed, utilizing a deep learning detection model to localize the joints and estimate their bending angles. This approach provides a non-intrusive, sensor-free alternative to hardware-based measurement methods, reducing complexity and wiring typically associated with wearable devices. Experimental results demonstrate the effectiveness of the proposed actuator in achieving bending angles of 105 degrees for the metacarpophalangeal (MCP) joint and 95 degrees for the proximal interphalangeal (PIP) joint, as well as a gripping force of 9.3 N. The vision system also captures bending angles with a precision of 98%, indicating potential applications in fields such as rehabilitation and human–robot interaction.
format Article
id doaj-art-9b914368cc2d4eda9b6d986e39a1e36d
institution OA Journals
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-9b914368cc2d4eda9b6d986e39a1e36d2025-08-20T02:36:22ZengMDPI AGSensors1424-82202025-06-012513385810.3390/s25133858Design and Evaluation of a Soft Robotic Actuator with Non-Intrusive Vision-Based Bending MeasurementNarges Ghobadi0Witold Kinsner1Tony Szturm2Nariman Sepehri3Department of Mechanical Engineering, Price Faculty of Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, CanadaDepartment of Electrical & Computer Engineering, Price Faculty of Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, CanadaRady Faculty of Health Sciences, College of Rehabilitation Sciences, University of Manitoba, Winnipeg, MB R3E 0T4, CanadaDepartment of Mechanical Engineering, Price Faculty of Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, CanadaThis paper presents the design and evaluation of a novel soft pneumatic actuator featuring two independent bending chambers, enabling independent joint actuation and localization for rehabilitation purposes. The actuator’s dual-chamber configuration provides flexibility for applications requiring customized bending profiles. To measure the bending angle of the finger joints in real time, a camera-based system is employed, utilizing a deep learning detection model to localize the joints and estimate their bending angles. This approach provides a non-intrusive, sensor-free alternative to hardware-based measurement methods, reducing complexity and wiring typically associated with wearable devices. Experimental results demonstrate the effectiveness of the proposed actuator in achieving bending angles of 105 degrees for the metacarpophalangeal (MCP) joint and 95 degrees for the proximal interphalangeal (PIP) joint, as well as a gripping force of 9.3 N. The vision system also captures bending angles with a precision of 98%, indicating potential applications in fields such as rehabilitation and human–robot interaction.https://www.mdpi.com/1424-8220/25/13/3858soft pneumatic actuatorvision systemsoft robotsrehabilitationjoint localization
spellingShingle Narges Ghobadi
Witold Kinsner
Tony Szturm
Nariman Sepehri
Design and Evaluation of a Soft Robotic Actuator with Non-Intrusive Vision-Based Bending Measurement
Sensors
soft pneumatic actuator
vision system
soft robots
rehabilitation
joint localization
title Design and Evaluation of a Soft Robotic Actuator with Non-Intrusive Vision-Based Bending Measurement
title_full Design and Evaluation of a Soft Robotic Actuator with Non-Intrusive Vision-Based Bending Measurement
title_fullStr Design and Evaluation of a Soft Robotic Actuator with Non-Intrusive Vision-Based Bending Measurement
title_full_unstemmed Design and Evaluation of a Soft Robotic Actuator with Non-Intrusive Vision-Based Bending Measurement
title_short Design and Evaluation of a Soft Robotic Actuator with Non-Intrusive Vision-Based Bending Measurement
title_sort design and evaluation of a soft robotic actuator with non intrusive vision based bending measurement
topic soft pneumatic actuator
vision system
soft robots
rehabilitation
joint localization
url https://www.mdpi.com/1424-8220/25/13/3858
work_keys_str_mv AT nargesghobadi designandevaluationofasoftroboticactuatorwithnonintrusivevisionbasedbendingmeasurement
AT witoldkinsner designandevaluationofasoftroboticactuatorwithnonintrusivevisionbasedbendingmeasurement
AT tonyszturm designandevaluationofasoftroboticactuatorwithnonintrusivevisionbasedbendingmeasurement
AT narimansepehri designandevaluationofasoftroboticactuatorwithnonintrusivevisionbasedbendingmeasurement