Combined adaptive-robust and neural network control of RLED robot manipulators using backstepping design

In this paper, a combined adaptive-robust and neural network control using backstepping design is proposed for trajectory tracking of non-redundant RLED robot manipulators. First, using the adaptive-robust algorithm, the current vector is regarded as the control variable for mechanical subsystem and an embedded control input for the desired current vector is designed so that the tracking goal may be achieved. Second, using neural network controller for DC motor dynamics, the voltage commands are designed such that the joint currents track their desired valued. The simplicity of the control law and low computational load are two main advantages of the adaptive-robust method. Also, the proposed control algorithm does not require the mathematical model representing the robot and its actuator dynamics. The robot parameters and neural weights are adapted on-line. Simulation results of application of the proposed scheme on a 5-DOF RLED robot manipulator are presented which show the efficiency and usefulness of the scheme