Robotic position/orientation control using neural networks

Abstract

This paper studies the use of neural networks in robotic position/orientation control. The process is divided into two tasks, i.e., the inverse kinematics solution and the adaptive motor control. Simulation results of a three-link robotic arm in a two-dimensional workspace demonstrate the validity of the design. The hierarchal nature of the design allows it to be applied to more complicated systems that operate in a three-dimensional workspace.