Improving the Accuracy of a Robot by Using Neural Networks (Neural Compensators and Nonlinear Dynamics)

The subject of this paper is a programmable con trol system for robotic manipulator. Considering the complex nonlinear dynamics involved in practical applications systems and arms, traditional control method here replaced by designed Elma adaptive radial basis function neural network—thereby improving stability response rate. Related controllers compensators were developed trained using MATLAB-related software. training results two network robot programming trajectories are presented dynamic errors different types methods analyzed.