Visual sensor integration on servoing the autonomous mobile robot

In this paper we proposed a visual servoing system for mobile robot navigation under omnidirectional vision and used an eye-to-hand camera to do color configuration. We used only one fixed camera to provide the picture for the global path planning. The image is captured by the omnidirectional camera mounted on the ceiling followed by camera calibration, image processing, path planning and target detection. The shortest path is found by Voronoi Diagram. When the mobile robot was moving, we used the feedback system to correct the location of the robot which reduced complexity for real-time operation. The experimental results demonstrated the effectiveness and efficiency of the proposed visual servoing algorithm.