Neural network adaptive control of a space platform-based deployable manipulator

Abstract

This paper presents a neural network based adaptive controller for an innovative space platform-based manipulator, which has a deployable link as well as a revolute joint The prototype manipulator system, which has been developed by us, is described. The analytical formulation of the system is presented with the objective of effective control. A single-layer, linear-in-the-parameter (LIP) neural network is used to approximate the unknown terms in the dynamical equations of the manipulator. The applicability and effectiveness of the neural-network control scheme for this manipulator system are tested through computer simulations.