Research On Navigation And Localization Algorithms For Power Substation Patrol Robot

With the fast development of new technology in artificial intelligence and computer vision, mobile robot has become the focus topic in the field of robotics and automation. Autonomous navigation and localization are key technologies in mobile robot system. Whether mobile robot could be applied in the practical environment depends on high localization precision and successful obstacle detection. In this research, navigation and localization methods by combination of RFID and stereovision developed for the patrol robot in power substation environment are presented. The main work is as followed:Patrol robot is localized by using RFID and vision. Firstly, the robot is localized globally by the RFID tags which are laid at critical junction of the road. Secondly, the artificial landmark, which is laid in the same location as RFID tag is, is recognized by vision, and the distance between robot and landmark is computed to locate the robot precisely. Finally, the robot is guided by the navigation orders provided by RFID tags to turn left, turn right, go forward, photo automatically and so on.Firstly, the road model hypothesis of the robot's power substation environment is proposed. Secondly, the distance between the obstacle and the camera is computed on the basis of the algorithm of binocular distance measurement. And then with the selected sample in the disparity image, the road plane equation of the current frame is calculated by the improved RANSAC algorithm. When the distance between the obstacle and the road is calculated on basis of the formula from the point to the plane, and the elevation image is obtained. Finally, some basic image processing methods are used for processing the terrain elevation map, and robot is navigated by the elevation image in combination with the road edges.Based on the theory mentioned above, the navigation and localization system for patrol robot is researched, and the friendly user interface is designed in the PC, using Windows Operation System, Microsoft Visual Studio 2005, OpenCV, as well as Digiclops SDK and Triclops Stereo SDK included with the Bumblebeeâ…¡as development environment. The practical application in substation environment verified the reliability of the system.