A fuzzy neural network-based fractional-order Lyapunov-based robust control strategy for exoskeleton robots: Application in upper-limb rehabilitation

Razzaghian, Amir

doi:10.1016/j.matcom.2021.10.022

Cited by 34 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where, u ∈ R is the input, y ∈ R is the measurable output and d ∈ R is a bounded disturbance. The model-free control approach proposed by Fliess 29 suggests approximating this system locally using an ultra-local model, as shown in Equation (17), where the unknown term F(t) can be estimated. Once F(t) is estimated, a model-free controller can be designed and implemented to achieve control objectives.…”

Section: Ultra-local Modelmentioning

confidence: 99%

“…11 Researchers have also developed different control laws for exoskeletons, as reported in the literature. Some of these control laws are based on artificial intelligence tools such as neural networks, [12][13][14][15] fuzzy logic, 16 neuron-fuzzy, 17,18 sliding modes, 13,[19][20][21][22] Kalman filters, 23 backstepping, 13,[24][25][26] and PID. 27 Despite significant progress in exoskeleton research, several challenges are still encountered during their operation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Model‐free based adaptive finite time control with multilayer perceptron neural network estimation for a 10 DOF lower limb exoskeleton

Kenas,

Saadia,

Ababou

et al. 2023

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryThis article presents a Model‐Free Adaptive Nonsingular Fast Terminal Sliding Mode Controller with Super Twisting and Multi‐Layer Perceptron (MLP) neural network for motion control of a 10 DOFs lower limb exoskeleton used in rehabilitation. The proposed controller employs a second‐order ultra‐local model to replace the complex dynamics of the exoskeleton and uses an MLP neural network to estimate the lumped disturbance of the ultra‐local model. To ensure accurate tracking of the desired trajectory and address the estimation errors of the MLP, an Adaptive Nonsingular Fast Terminal Sliding Mode Controller is introduced. Moreover, a Super Twisting approach is employed to eliminate the chattering phenomenon. The system's stability is analyzed using Lyapunov theory, and the desired trajectories are obtained from surface electromyography (EMG) signal measurements. The effectiveness of the proposed controller is validated through co‐simulation experiments using SolidWorks, Simscape Multibody, and MATLAB/Robotics Toolbox. Results demonstrate significant improvements in stability and precision compared to existing model‐free controllers.

show abstract

Section: Ultra-local Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Model‐free based adaptive finite time control with multilayer perceptron neural network estimation for a 10 DOF lower limb exoskeleton

Kenas,

Saadia,

Ababou

et al. 2023

Adaptive Control & Signal

View full text Add to dashboard Cite

show abstract

“…Since the inner loop controller (14) contains uncertainty term F(ω), it is necessary to construct T1FNN to compensate. The structure of T1FNN is based on fuzzy rules, and the expression form of fuzzy rules is (16) [37].…”

Section: Design Of T1fnnmentioning

confidence: 99%

Predefined-Time Fuzzy Neural Network Control for Omnidirectional Mobile Robot

et al. 2022

View full text Add to dashboard Cite

In this paper, a fuzzy neural network based predefined-time trajectory tracking control method is proposed for the tracking problem of omnidirectional mobile robots (FM-OMR) with uncertainties. Considering the requirement of tracking error convergence time, a position tracking controller based on predefined-time stability is proposed. Compared with the traditional position tracking control method, the minimum upper bound of the convergence time can be explicitly set. In order to obtain more accurate angular velocity tracking, the inner loop controller combines Type 1 fuzzy neural network (T1FNN) to estimate the uncertainty. In addition, considering the problem of feedback channel noise, a Kalman filter combining velocity and position information is proposed. Finally, the simulation results verify the effectiveness of this method.

show abstract

“…Several studies based on intelligent learning control have been performed for rehabilitation purposes, as in the work by Mirrashid et al 17 The authors presented a controller for regulation of lower limbs using a fuzzy adaptation approach. Furthermore, Razzaghian 18 proposed an artificial neural network controller to help patients to achieve effective rehabilitation therapy using active orthoses for lower limbs. Several modeling and control techniques have been explored, including intelligent control based on fuzzy logic approaches and sliding mode 19 and/or both.…”

Section: Introductionmentioning

confidence: 99%

Flatness tracking control scheme of rehabilitation exoskeleton robot with dynamic uncertainties

Bououden

Brahmi

Rahman

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

Artificial limbs are new robotic devices created to help stroke victims in the rehabilitation process. In this article, we focus our work on applying passive, active or assistive control strategies to provide a physical assistance and rehabilitation by a 7-degree-of-freedom exoskeleton robot with nonlinear uncertain dynamics and unknown bounded external disturbances due to the robot user’s physiological characteristics. The flatness controller combined with time-delay estimation is designed for the 7-degree-of-freedom exoskeleton robot called ETS-MARSE (Ecole de Technologie Supérieure—Motion Assistive Robotic-exoskeleton for Superior Extremity) in order to ensure a passive rehabilitation exercises with a high level of tracking accuracy and robustness against the uncertainty constraints. The stability analysis of such systems is proven using the Lyapunov–Krasovskii functional theory. This approach is illustrated by experimental results with healthy human to highlight the efficiency of the suggested controller scheme.

show abstract

A fuzzy neural network-based fractional-order Lyapunov-based robust control strategy for exoskeleton robots: Application in upper-limb rehabilitation

Cited by 34 publications

References 35 publications

Model‐free based adaptive finite time control with multilayer perceptron neural network estimation for a 10 DOF lower limb exoskeleton

Model‐free based adaptive finite time control with multilayer perceptron neural network estimation for a 10 DOF lower limb exoskeleton

Predefined-Time Fuzzy Neural Network Control for Omnidirectional Mobile Robot

Flatness tracking control scheme of rehabilitation exoskeleton robot with dynamic uncertainties

Contact Info

Product

Resources

About