Real-time implementation of neural network learning control of a flexible Space manipulator

Abstract

A neural network approach to online learning control and real-time implementation for a flexible space robot manipulator is presented. An overview of the motivation and system development of the self-mobile space modulator (SM/sup 2/) is given. The neural network learns control by updating feedforward dynamics based on feedback control input. Implementation issues associated with online training strategies are addressed and a single stochastic training scheme is presented. A recurrent neural network architecture with improved performance is proposed. Using the proposed learning scheme, the manipulator tracking error is reduced by 85% compared to that of conventional proportional-integral-derivative (PID) control. The approach possesses a high degree of generality and adaptability to various applications. It will be a valuable learning control method for robots working in unconstructed environments.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>