Visual Attention Control for Nuclear Power Plant Inspection

Industrial inspection robots, which are to move around a nuclear power plant and carry out inspection tasks, must follow a given route while observing static and dynamic features of the environment. To fulfill the visual sensing requirements of such a robot for both a wide field of view to ensure safe motion and high resolution to enable precise observation, we have developed a stereo active vision system equipped with foveated wide-field image acquisition and mounted it on a mobile robot. With this or other types of active sensors, only the foveated center of the field of view can extract precise information, so the camera pose must be controlled to fixate the target area for execution of a particular visual task. The activities of inspection robots lead to multiple visual tasks, requiring both reactive and premeditated types of attention, and therefore the robot must apply its sensing resources sequentially among multiple possibilities. In this paper, we propose a new framework for visual attention control for a mobile robot, describe the implementation of the proposed framework and show some examples in which the camera pose is controlled to achieve multiple visual tasks.