Identification and Position Control of a Continuum Robotic Arm

Abstract

Compared to traditional robots, continuum robotic arms have many advantages, including higher maneuverability, lower cost and weight, secure operation and so on, which motivate researchers in this field. Modeling and identifying these systems are very important due to their use in control applications; however, due to the complex nonlinear nature and presence of uncertainties, achieving an appropriate model is a great challenge. In this paper, after evaluating the repeatability of the system, which influences the model identification, the NARX model is presented and neural network is employed for developing the model. The model is validated by the experimental results. Then, contolling the end-effector position of the system using the identified model is performed.