This paper presents an algorithm to track an industrial robot hand during its movement. Based on acquired image and knowing the robot hand model, the pose is obtained. This information is used to move a pan-tilt camera and keep the robot hand centered in the image every time using an adaptive fuzzy logic controlled. This control law is used combined with a position prediction technique to improve the system behavior. Vision based systems have a lot of empirically adjustable parameters for a good working. With the algorithm proposed in this paper, the adjustable parameters are minimum, so the system robustness is increased. Keywords Tracking, computer vision, fuzzy control, applications.