Adaptive versus neural adaptive control: Application to robotics

Abstract

Abstract A comparative study evaluates the problem of determining the control that must be exerted on manipulator joints. Two different techniques are studied: (i) direct and indirect adaptive controls and (ii) neural adaptive control. In the direct adaptive technique the Lyapunov stability‐based approach is used with the objective of minimizing the tracking errors of the joints in the adaptation process. In the indirect adaptive technique the regulator parameters are updated via the estimation of the process model. This step, using a recursive least squares algorithm, is based on the error at the input and on the filtered dynamic model in order to avoid acceleration measurements. Neural adaptive control is based on learning from input‐output measurements and not on parametricmodel‐based dynamics. It is important to note that adaptive control requires a real‐time estimation of the system parameters and a well‐defined dynamic model, whereas neural adaptive control does not require any of these conditions. All the above‐mentioned techniques are applied to the trajectory‐tracking control of a two‐degree‐of‐freedom (2DOF) manipulator. the experimental results show the effectiveness of the neural adaptive techniques for the trajectory‐tracking errors.