Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation
Abstract The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper extremities. Here, we introduce an intelligent upper-limb exoskeleton system that utilizes deep learning to predict human intention for strength augmentation....
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | npj Flexible Electronics |
| Online Access: | https://doi.org/10.1038/s41528-024-00297-0 |
| _version_ | 1827325854119624704 |
|---|---|
| author | Jinwoo Lee Kangkyu Kwon Ira Soltis Jared Matthews Yoon Jae Lee Hojoong Kim Lissette Romero Nathan Zavanelli Youngjin Kwon Shinjae Kwon Jimin Lee Yewon Na Sung Hoon Lee Ki Jun Yu Minoru Shinohara Frank L. Hammond Woon-Hong Yeo |
| author_facet | Jinwoo Lee Kangkyu Kwon Ira Soltis Jared Matthews Yoon Jae Lee Hojoong Kim Lissette Romero Nathan Zavanelli Youngjin Kwon Shinjae Kwon Jimin Lee Yewon Na Sung Hoon Lee Ki Jun Yu Minoru Shinohara Frank L. Hammond Woon-Hong Yeo |
| author_sort | Jinwoo Lee |
| collection | DOAJ |
| description | Abstract The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper extremities. Here, we introduce an intelligent upper-limb exoskeleton system that utilizes deep learning to predict human intention for strength augmentation. The embedded soft wearable sensors provide sensory feedback by collecting real-time muscle activities, which are simultaneously computed to determine the user’s intended movement. Cloud-based deep learning predicts four upper-limb joint motions with an average accuracy of 96.2% at a 500–550 ms response rate, suggesting that the exoskeleton operates just by human intention. In addition, an array of soft pneumatics assists the intended movements by providing 897 newtons of force while generating a displacement of 87 mm at maximum. The intent-driven exoskeleton can reduce human muscle activities by 3.7 times on average compared to the unassisted exoskeleton. |
| first_indexed | 2024-03-07T14:35:22Z |
| format | Article |
| id | doaj.art-de0a1898b29c431bb6764a0d345a5630 |
| institution | Directory Open Access Journal |
| issn | 2397-4621 |
| language | English |
| last_indexed | 2024-03-07T14:35:22Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Flexible Electronics |
| spelling | doaj.art-de0a1898b29c431bb6764a0d345a56302024-03-05T20:41:42ZengNature Portfolionpj Flexible Electronics2397-46212024-02-018111310.1038/s41528-024-00297-0Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentationJinwoo Lee0Kangkyu Kwon1Ira Soltis2Jared Matthews3Yoon Jae Lee4Hojoong Kim5Lissette Romero6Nathan Zavanelli7Youngjin Kwon8Shinjae Kwon9Jimin Lee10Yewon Na11Sung Hoon Lee12Ki Jun Yu13Minoru Shinohara14Frank L. Hammond15Woon-Hong Yeo16Department of Mechanical, Robotics, and Energy Engineering, Dongguk UniversityIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyGeorge W. Woodruff School of Mechanical Engineering, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologySchool of Electrical and Electronic Engineering, Yonsei UniversityIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyGeorge W. Woodruff School of Mechanical Engineering, Georgia Institute of TechnologyIEN Center for Wearable Intelligent Systems and Healthcare, Institute for Electronics and Nanotechnology, Georgia Institute of TechnologyAbstract The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper extremities. Here, we introduce an intelligent upper-limb exoskeleton system that utilizes deep learning to predict human intention for strength augmentation. The embedded soft wearable sensors provide sensory feedback by collecting real-time muscle activities, which are simultaneously computed to determine the user’s intended movement. Cloud-based deep learning predicts four upper-limb joint motions with an average accuracy of 96.2% at a 500–550 ms response rate, suggesting that the exoskeleton operates just by human intention. In addition, an array of soft pneumatics assists the intended movements by providing 897 newtons of force while generating a displacement of 87 mm at maximum. The intent-driven exoskeleton can reduce human muscle activities by 3.7 times on average compared to the unassisted exoskeleton.https://doi.org/10.1038/s41528-024-00297-0 |
| spellingShingle | Jinwoo Lee Kangkyu Kwon Ira Soltis Jared Matthews Yoon Jae Lee Hojoong Kim Lissette Romero Nathan Zavanelli Youngjin Kwon Shinjae Kwon Jimin Lee Yewon Na Sung Hoon Lee Ki Jun Yu Minoru Shinohara Frank L. Hammond Woon-Hong Yeo Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation npj Flexible Electronics |
| title | Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation |
| title_full | Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation |
| title_fullStr | Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation |
| title_full_unstemmed | Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation |
| title_short | Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation |
| title_sort | intelligent upper limb exoskeleton integrated with soft bioelectronics and deep learning for intention driven augmentation |
| url | https://doi.org/10.1038/s41528-024-00297-0 |
| work_keys_str_mv | AT jinwoolee intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT kangkyukwon intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT irasoltis intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT jaredmatthews intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT yoonjaelee intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT hojoongkim intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT lissetteromero intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT nathanzavanelli intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT youngjinkwon intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT shinjaekwon intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT jiminlee intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT yewonna intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT sunghoonlee intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT kijunyu intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT minorushinohara intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT franklhammond intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation AT woonhongyeo intelligentupperlimbexoskeletonintegratedwithsoftbioelectronicsanddeeplearningforintentiondrivenaugmentation |