TY - JOUR
T1 - Utilizing the intelligence edge framework for robotic upper limb rehabilitation in home
AU - Jamwal, Prashant K.
AU - Niyetkaliyev, Aibek
AU - Hussain, Shahid
AU - Sharma, Aditi
AU - Van Vliet, Paulette
N1 - Publisher Copyright:
© 2023 The Author(s)
PY - 2023/12
Y1 - 2023/12
N2 - Robotic devices are gaining popularity for the physical rehabilitation of stroke survivors. Transition of these robotic systems from research labs to the clinical setting has been successful, however, providing robot-assisted rehabilitation in home settings remains to be achieved. In addition to ensure safety to the users, other important issues that need to be addressed are the real time monitoring of the installed instruments, remote supervision by a therapist, optimal data transmission and processing. The goal of this paper is to advance the current state of robot-assisted in-home rehabilitation. A state-of-the-art approach to implement a novel paradigm for home-based training of stroke survivors in the context of an upper limb rehabilitation robot system is presented in this paper. First, a cost effective and easy-to-wear upper limb robotic orthosis for home settings is introduced. Then, a framework of the internet of robotics things (IoRT) is discussed together with its implementation. Experimental results are included from a proof-of-concept study demonstrating that the means of absolute errors in predicting wrist, elbow and shoulder angles are 0.89180,2.67530 and 8.02580, respectively. These experimental results demonstrate the feasibility of a safe home-based training paradigm for stroke survivors. The proposed framework will help overcome the technological barriers, being relevant for IT experts in health-related domains and pave the way to setting up a telerehabilitation system increasing implementation of home-based robotic rehabilitation. The proposed novel framework includes: • A low-cost and easy to wear upper limb robotic orthosis which is suitable for use at home. • A paradigm of IoRT which is used in conjunction with the robotic orthosis for home-based rehabilitation. • A machine learning-based protocol which combines and analyse the data from robot sensors for efficient and quick decision making.
AB - Robotic devices are gaining popularity for the physical rehabilitation of stroke survivors. Transition of these robotic systems from research labs to the clinical setting has been successful, however, providing robot-assisted rehabilitation in home settings remains to be achieved. In addition to ensure safety to the users, other important issues that need to be addressed are the real time monitoring of the installed instruments, remote supervision by a therapist, optimal data transmission and processing. The goal of this paper is to advance the current state of robot-assisted in-home rehabilitation. A state-of-the-art approach to implement a novel paradigm for home-based training of stroke survivors in the context of an upper limb rehabilitation robot system is presented in this paper. First, a cost effective and easy-to-wear upper limb robotic orthosis for home settings is introduced. Then, a framework of the internet of robotics things (IoRT) is discussed together with its implementation. Experimental results are included from a proof-of-concept study demonstrating that the means of absolute errors in predicting wrist, elbow and shoulder angles are 0.89180,2.67530 and 8.02580, respectively. These experimental results demonstrate the feasibility of a safe home-based training paradigm for stroke survivors. The proposed framework will help overcome the technological barriers, being relevant for IT experts in health-related domains and pave the way to setting up a telerehabilitation system increasing implementation of home-based robotic rehabilitation. The proposed novel framework includes: • A low-cost and easy to wear upper limb robotic orthosis which is suitable for use at home. • A paradigm of IoRT which is used in conjunction with the robotic orthosis for home-based rehabilitation. • A machine learning-based protocol which combines and analyse the data from robot sensors for efficient and quick decision making.
KW - Internet of things
KW - Inverse kinematics
KW - Machine learning
KW - Stroke
KW - Visual servoing
UR - http://www.scopus.com/inward/record.url?scp=85166971811&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85166971811&partnerID=8YFLogxK
U2 - 10.1016/j.mex.2023.102312
DO - 10.1016/j.mex.2023.102312
M3 - Article
AN - SCOPUS:85166971811
SN - 2215-0161
VL - 11
JO - MethodsX
JF - MethodsX
M1 - 102312
ER -