Adaptive Backstepping-RBF Control of Lower Limb Exoskeleton

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

“…Additionally, these devices can be useful for functional rehabilitation in cases of physical deficiencies. 1 Several studies have been conducted on the design of exoskeletons, including systems for the lower limbs such as BLEEX, 2,3 HAL, 4,5 LOPES, 6 or NUS, 7 systems for the upper limbs such as ATLAS, 8 NESM, 9 CAREX, 10 and systems for both lower and upper body parts. 11 Researchers have also developed different control laws for exoskeletons, as reported in the literature.…”

“…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.…”

“…One such solution is the development of exoskeletons, which can provide physical assistance and improve the motor skills of the elderly. Additionally, these devices can be useful for functional rehabilitation in cases of physical deficiencies 1 …”

“…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, 12–15 fuzzy logic, 16 neuron‐fuzzy, 17,18 sliding modes, 13,19–22 Kalman filters, 23 backstepping, 13,24–26 and PID 27 …”

“…Consequently, many studies are focusing on handling these problems and reducing the complexity of the dynamic model of the system. For example, researchers in References 13,19 utilized neural networks to estimate the uncertainties of the dynamic model of the exoskeleton and enhance the accuracy and stability of the system. Additionally, other studies employed disturbance observers in the design of controllers to minimize the impact of uncertainties and disturbances 25,28 …”