EYE-IN-HAND 3D ROBOTIC VISUAL TRACKING WITHOUT CALIBRATION

Abstract

In this paper, without explicit external and internal calibration, a nonlinear visual mapping model for 3D robotic visual tracking problem is proposed and a new visual tracking controller based on artificial neural network is designed. Simulation results show that this method can drive the static tracking error to zero quickly and keep good robustness and adaptability at the same time. Additionally, the algorithm is very easy to be implemented with low computational complexity.