Robotic eye/arm coordination via visual servoing

Robotic eye/arm coordination has recently enjoyed much attention. This paper presents the coordinated control of the eyes in the robotic binocular head and the robot arm. This paper proposes an image-based visual servo control method for the binocular head, which integrates the kinematics of both the robotic head and cameras with the dynamics of the head to obtain an image-based dynamic equation. The fuzzy sliding mode control algorithm is applied to the image-based dynamic equation for the robotic head to trace the target and keep it at the centers of both image planes of two CCD cameras in the presence of model uncertainties and disturbances. Additionally, this paper proposes a coordinated visual guided control strategy for the eyes in the robotic head and robot arm, which is an end point open-loop control method. The coordinated control strategy proposed herein is based on the coordination transformation from the head to the arm, which is calibrated off-line. To illustrate and verify the theoretical derivations, a robot arm equipped with a laser pointer is controlled to focus a laser beam on a moving size-changing target on the screen of a monitor, while the eyes in a binocular head trace the target.