Continuous-Time Neural Identification for a 2 DOF Vertical Robot Manipulator

A Recurrent High-Order Neural Network (RHONN) structure as well as a decentralized neural network scheme, this latter with high-order interconnections, are proposed to execute continuous-time identification of a two degrees of freedom (DOF) direct drive vertical planar robot manipulator model, on which effects due to friction and gravity forces are both considered. The neural network learning is achieved online using the filtered error approach. The performance of both neural networks schemes is illustrated via simulation results.