A focused review on upper and lower limb joint torque estimation via neural networks

Joint torque estimation is an essential aspect of the control architecture in assistive devices for rehabilitation and aiding movement impairments. Healthy adult torque trajectories serve as a baseline for controllers to determine the level of assistance required by patients, evaluate impaired motio...

Full description

Bibliographic Details
Main Authors: Perera, Chamalka Kenneth, Gopalai, Alpha Agape, Gouwanda, Darwin, Ahmad, Siti Anom
Format: Article
Language:English
Published: Universiti Putra Malaysia Press 2025
Online Access:http://psasir.upm.edu.my/id/eprint/120951/
http://psasir.upm.edu.my/id/eprint/120951/1/120951.pdf
_version_ 1848868256210747392
author Perera, Chamalka Kenneth
Gopalai, Alpha Agape
Gouwanda, Darwin
Ahmad, Siti Anom
author_facet Perera, Chamalka Kenneth
Gopalai, Alpha Agape
Gouwanda, Darwin
Ahmad, Siti Anom
author_sort Perera, Chamalka Kenneth
building UPM Institutional Repository
collection Online Access
description Joint torque estimation is an essential aspect of the control architecture in assistive devices for rehabilitation and aiding movement impairments. Healthy adult torque trajectories serve as a baseline for controllers to determine the level of assistance required by patients, evaluate impaired motion, understand biomechanics, and design treatment plans. Currently, methods of torque estimation include inverse dynamics using gold standard motion capture systems, generic mathematical models based on joint torque-angle relationships, neuromusculoskeletal modelling using surface electromyography, and neural networks. As such, this review provides a focused overview of the recent and existing neural networks tailored for upper and lower limb joint torque estimation. Dataset preparation, data preprocessing, and evaluation metrics are presented along with a detailed description of the developed networks, which are classified by model architecture. It includes artificial neural networks (ANNs), convolution neural networks (CNNs), long short-term memory (LSTM) networks, and hybrid and alternate architectures such as wavelet or explainable convolution (XCM). The performance, benefits, and limitations of the models are discussed, highlighting CNNs and LSTMs as the current optimal models for time series prediction of joint torque. This is due to their ability to capture spatial and temporal dependencies in the data. Additionally, joint kinematics such as angles, angular velocities, and accelerations are considered optimal input parameters due to their ease of measurement using wearable sensors and integration with wearable assistive technology.
first_indexed 2025-11-15T14:49:30Z
format Article
id upm-120951
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:49:30Z
publishDate 2025
publisher Universiti Putra Malaysia Press
recordtype eprints
repository_type Digital Repository
spelling upm-1209512025-10-16T07:23:16Z http://psasir.upm.edu.my/id/eprint/120951/ A focused review on upper and lower limb joint torque estimation via neural networks Perera, Chamalka Kenneth Gopalai, Alpha Agape Gouwanda, Darwin Ahmad, Siti Anom Joint torque estimation is an essential aspect of the control architecture in assistive devices for rehabilitation and aiding movement impairments. Healthy adult torque trajectories serve as a baseline for controllers to determine the level of assistance required by patients, evaluate impaired motion, understand biomechanics, and design treatment plans. Currently, methods of torque estimation include inverse dynamics using gold standard motion capture systems, generic mathematical models based on joint torque-angle relationships, neuromusculoskeletal modelling using surface electromyography, and neural networks. As such, this review provides a focused overview of the recent and existing neural networks tailored for upper and lower limb joint torque estimation. Dataset preparation, data preprocessing, and evaluation metrics are presented along with a detailed description of the developed networks, which are classified by model architecture. It includes artificial neural networks (ANNs), convolution neural networks (CNNs), long short-term memory (LSTM) networks, and hybrid and alternate architectures such as wavelet or explainable convolution (XCM). The performance, benefits, and limitations of the models are discussed, highlighting CNNs and LSTMs as the current optimal models for time series prediction of joint torque. This is due to their ability to capture spatial and temporal dependencies in the data. Additionally, joint kinematics such as angles, angular velocities, and accelerations are considered optimal input parameters due to their ease of measurement using wearable sensors and integration with wearable assistive technology. Universiti Putra Malaysia Press 2025 Article PeerReviewed text en cc_by_nc_nd_4 http://psasir.upm.edu.my/id/eprint/120951/1/120951.pdf Perera, Chamalka Kenneth and Gopalai, Alpha Agape and Gouwanda, Darwin and Ahmad, Siti Anom (2025) A focused review on upper and lower limb joint torque estimation via neural networks. Pertanika Journal of Science and Technology, 33 (1). pp. 121-147. ISSN 0128-7680; eISSN: 2231-8526 http://pertanika2.upm.edu.my/pjst/browse/regular-issue?article=JST-5047-2024 10.47836/pjst.33.1.06
spellingShingle Perera, Chamalka Kenneth
Gopalai, Alpha Agape
Gouwanda, Darwin
Ahmad, Siti Anom
A focused review on upper and lower limb joint torque estimation via neural networks
title A focused review on upper and lower limb joint torque estimation via neural networks
title_full A focused review on upper and lower limb joint torque estimation via neural networks
title_fullStr A focused review on upper and lower limb joint torque estimation via neural networks
title_full_unstemmed A focused review on upper and lower limb joint torque estimation via neural networks
title_short A focused review on upper and lower limb joint torque estimation via neural networks
title_sort focused review on upper and lower limb joint torque estimation via neural networks
url http://psasir.upm.edu.my/id/eprint/120951/
http://psasir.upm.edu.my/id/eprint/120951/
http://psasir.upm.edu.my/id/eprint/120951/
http://psasir.upm.edu.my/id/eprint/120951/1/120951.pdf