Mainly present in industry, robots begin to invade our every-day lives for very precise tasks. In order to reach a level where more general robots get involved in our lives, the robots' abilities to communicate and to react to unexpected situations must be improved. This paper introduces an attentive computational model for robots as attention can help both in reacting to unexpected situations and to help improving human-robot communication. We propose to enhance and implement an existing real time computational model. Intensity, color and orientation are usually used but we have added information related to depth and isolation. We have built a robotic system based on LEGO Mindstorm platform and the Kinect RGB-D sensor. This robot, called CuriousMind, is able to take a picture of the most interesting part of the scene and it can also be distracted from its first goal by novel situations mimicking in that way the human (and more precisely small children) behaviour.