A Method for Localization by Integration of Imprecise Vision and a Field Model

In recent years, many researchers in AI and Robotics pay attention to RoboCup, because robotic soccer games needs various techniques in AI and Robotics, such as navigation, behavior generation, localization and environment recognition. Localization is one of the important issues for RoboCup. In this paper, we propose a method o f r obot's localization by integrating vision and modeling of the environment. The environment model that realizes the robotic soccer led in the computer can produce an image of robot's view at any location. In the environment model, the system can search and appropriate location of which view image is similar to the view image by the real robot. Our robot can estimate location form goal's height and aspect ratio on the camera image. We search the most suitable position with hill-climbing algorithm form the estimated l o-cation. We programmed this method, and tested v a-lidity. The error range is reduced form 1m50cm by robot's estimation from 40cm20cm by this method. This method i s s u p erior to the other methods using dead reckoning or range sensor with map because it does not depend on the eld size on precision, and does not need walls as landmark.