Adaptive tracking control of hydraulic robot manipulator using hybrid intelligent system (ANFIS)

The motion control of an experimental hydraulically actuated robot with structured uncertainty (parameter uncertainty, unknown loads, inaccuracies in the torque constants of the actuators, and others) and unstructured uncertainty (high-frequency modes, neglected time-delays, unknown friction forces, stick-slip oscillations, and unknown oil viscosity, etc...) is considered. As a solution we propose two control techniques based on ANFIS: Adaptive Neuro Fuzzy Inference System based computed torque controller (type PD), and Adaptive Neuro Fuzzy Inference System based PD plus I controller. Comparative evaluations with respect to conventional PD controller are presented to validate the controllers design. The simulated and experimental results presented emphasize that a satisfactory tracking precision could be achieved using ANFIS controllers. Copyright © 2014 SoftMotor Ltd.