An eye-to-hand visual servoing structure for 3D positioning of a robotic arm using one camera and a flat mirror

This paper introduces a novel visual servoing structure for 3D robot positioning under an eye-to-hand camera configuration. The proposed algorithm is based on image-based visual servoing (IBVS) using only one camera in conjunction with a flat mirror. A landmark mounted on the robot along with its mirror reflection, when viewed by the camera, provides enough information for 3D reasoning based on a 2D image. The governing equations describing the relationship between the robot's velocity and rate of change in image features are fully described. Furthermore, a methodology for on-line estimation of the image Jacobian with no camera calibration is developed. Simulation and experimental results illustrate the robustness of the proposed visual servoing structure.