feedback error learning
Recently Published Documents


TOTAL DOCUMENTS

159
(FIVE YEARS 14)

H-INDEX

18
(FIVE YEARS 1)

2021 ◽  
Vol 54 (10) ◽  
pp. 182-188
Author(s):  
Dongyang Wang ◽  
Yuhki Hashimoto ◽  
Hiromitsu Ohmori

AIAA Journal ◽  
2020 ◽  
Vol 58 (7) ◽  
pp. 3229-3240
Author(s):  
Xiangshuai Song ◽  
Weimeng Chu ◽  
Shujun Tan ◽  
Zhigang Wu ◽  
Zhaohui Qi

2020 ◽  
Vol 56 (3) ◽  
pp. 141-148
Author(s):  
Wataru IMAHAYASHI ◽  
Xinyou HAN ◽  
Masaki OGURA ◽  
Kenji SUGIMOTO

Author(s):  
José González-Vargas ◽  
Mario Rios-Mora ◽  
Juan C. Moreno ◽  
José Luis Pons-Rovira

El presente documento abarca la mejora del esquema de control de los actuadores de rigidez variable (VSA), presentes en la articulación de la rodilla de un robot bípedo llamado Binocchio, desarrollado por el grupo de Neuro-rehabilitación del Instituto Cajal. El diseño de dicho robot se basó en varias características biológicas presentes en los seres humanos como por ejemplo la visco-elasticidad de los músculos. Para controlar estos actuadores de manera robusta y eficiente no es suficiente el uso de estrategias de control clásico basados en modelos, debido a que estos métodos no son capaces de tomar en cuenta todas las no-linealidades intrínsecas del actuador debido a su estructura mecánica y a su naturaleza elástica. Por ello se adaptó un método bio-inspirado de control conocido como Feedback Error Learning (FEL) que utiliza una red neuronal para aprender el modelo inverso sin ningún conocimiento a priori de los parámetros del actuador. Seguidamente se procedió a realizar pruebas de control para validar su implementación. Finalmente, fue posible adaptar el FEL para el control de los VSA, lo que incidió en una mejora significativa en el rendimiento de los controladores de trayectoria. Pruebas de robustez y de estabilidad permitieron validar el uso del FEL como una alternativa viable para el control de los actuadores.


2019 ◽  
Author(s):  
Makoto Eguchi ◽  
Naoki Fukuda ◽  
Hiromitsu Ohmori ◽  
Motoki Takahashi ◽  
Yudai Yamasaki ◽  
...  

Motivation: Upper-limb motor impairment is one of the most common consequences after Stroke. Limited capability for performing reaching and grasping movements hinders the execution of most activities of daily living. Consequently, the quality lives of the affected individuals are severely compromised. Due to these facts, the recovery of the upper limb functional capabilities is currently one of the keystones of the rehabilitation therapy. Background: Researchers are developing new methods and technologies to boost the outcomes of rehabilitation therapy. A hybrid robotic system has been proposed as a promising rehabilitation technology that combines a passive device (Armeo Spring exoskeleton) to support the arm weight against gravity with a Functional Electrical Stimulation (FES) system to execute the reaching task. This system provides to patients the possibility of training specifically and intensive exercises. Objective: The main objective of this paper is to investigate the performance and robustness of a Feedback Error learning (FEL) scheme mixed with sliding mode control (SMC) to control the FES. Methods: We implemented a nonlinear model describing the muscle response to FES and the dynamic behavior of the elbow joint. Using this model we carried out a simulation study to compare four control strategies: computed torque control (CTC), sliding mode Control (SMC), and adaptive feedback control using FEL: ANN+ CTC and FEL: ANN+SMC. We tested these controllers in two different simulation conditions: In the absence and presence of fatigue. To check the performance of the controllers, we compared the root means square (RMSE) of tracking error and the Normalized RMS of muscle stimulation for various range of movement (ROM). Results: All four controllers achieved good tracking performance in the absence of perturbations. When introducing muscle fatigue, good tracking performance is given essentially by the adaptive control ANN+SMC. Conclusion: Among the proposed approaches, we conclude that the adaptive control (FEL: ANN + SMC) is the most efficient and robust controller, which has been proven by calculating RMSE.


Sign in / Sign up

Export Citation Format

Share Document