Neural Networks For Robot Control

摘要

This report results from a contract tasking Lebanese University- Faculty of Engineering, Section I as follows: The proposed research consists of the following: (a) Application of artificial neural networks (multi-layer perceptrons, MLPs) for 2D planar robot arm by using the dynamic backpropagation methods for the adjustment of parameters; and optimization of the architecture; (b) Application of artificial neural networks in controlling closed-loop 2D planar robot arm and comparison with the use of proportional-integral- differential (PID) controllers. The results should create a basis for a further research program connecting the fundamental knowledge with practical applications that can subsequently include: (1) Theoretical and experimental studies in controlling dynamic robot arms by using neural networks in real-time process; (2) Research of optimal architectures used in closed-loop systems in order to compare with adaptive and robust control.