Genetic Algorithm-Based Sliding Mode Control of a Human Arm Model

Spinal cord injured patients cannot move their segments by their intact muscles. A suitable controller can be used to help them move their arm. In this study, the kinematics and dynamics of righth-and movement are modeled considering planar three links. A genetic algorithm-based sliding mode (GASM) controller is designed to move the human arm model for tracking a desired trajectory in the sagittal plane. The GA is used to tune the convergence rate of the sliding mode controller for having an appropriate tracking performance. The summation of errors is considered as a cost function and GA is proposed to find the controller gains to minimize the difference between the outputs of the model and nominal trajectories. To the best of the author's knowledge, it is for the first time that the GA-sliding mode controller has been used for controlling the human hand so as to have a particular movement. Simulation results are evaluated in upward and downward movements of the human arm to affirm the effectiveness of the proposed controller. Copyright (C) 2022 The Authors.

Automated summary

In this study, a genetic algorithm-based sliding mode controller is designed to assist spinal cord injured patients in controlling the movement of their arm. The kinematics and dynamics of the arm are modeled using planar three links, and a genetic algorithm is utilized to tune the convergence rate of the sliding mode controller for appropriate tracking performance.