Image-Based Visual Servoing Techniques for Robot Control

Abstract

Visual servoing involves extracting information from the image provided by cameras and integrating it into the robot control loop to achieve the desired action. Visual servoing techniques based on geometric primitives are effective for a large class of applications. In this paper, we present a comparison between points, line, and circle primitives in terms of feature error, computation time, and space velocity convergence of the vision sensor. The simulation results show the ability of visual servo techniques based on the three geometric primitives for controlling robots with superiority to line primitives in terms of computation time and speed of convergence.