Adaptive control of a robotic exoskeleton for enhanced knee rehabilitation
Vietnam Journal of Mechanics · 03.07.2026
DOI: 10.15625/0866-7136/23798 ↗Kurz gefasst
Fachartikel in der Zeitschrift Vietnam Journal of Mechanics, online erschienen am 03.07.2026. Verfasst von Duc Toan Luu und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Variable stiffness actuators (VSAs) offer significant potential for diverse applications due to their ability to adjust stiffness in response to operational requirements. The proposed VSA comprises 12 pairs of outer pulleys and six pairs of inner pulleys, uniformly arranged around a central axis and connected in series to a spring via a cable. Rotation of the inner pulleys around the center extends the spring, generating an elastic force that is transmitted through the cable to the output link, producing output torque and stiffness. The output stiffness varies with the angle of rotation, posing challenges for control system design. This study proposes machine learning-based approaches to achieve accurate and low-latency control. Specifically, neural network models are developed to estimate the spring preload at various actuator positions, enabling precise control of the desired stiffness. The results show that the Feedforward Neural Network enables the actuator to achieve a stiffness with a root-mean-square error of 0.0073 Ncm/degree.
Zitieren
APA
Luu, D. T., & Nguyen, V. L. (2026). Adaptive control of a robotic exoskeleton for enhanced knee rehabilitation. Vietnam Journal of Mechanics. https://doi.org/10.15625/0866-7136/23798
Vancouver
Luu DT, Nguyen VL. Adaptive control of a robotic exoskeleton for enhanced knee rehabilitation. Vietnam Journal of Mechanics. 2026. doi:10.15625/0866-7136/23798
BibTeX
@article{Luu2026,
author = {Luu, Duc Toan and Nguyen, Vu Linh},
title = {Adaptive control of a robotic exoskeleton for enhanced knee rehabilitation},
journal = {Vietnam Journal of Mechanics},
year = {2026},
doi = {10.15625/0866-7136/23798}
}
EUVIMED