Visual Protractor Based Localization Algorithm for Mobile Robot

Data fusion is an effective tool to improve the localization precision of a mobile robot. This paper presents a new algorithm to improve the precision of robot localization by fusing data from three kinds of sensors: encoders, a gyroscope and a camera. In the data fusion process, the camera is used as a visual protractor, which is a simple and robust way to process vision information but plays an important role in reducing the errors of localization in high slip-rate cases. An experiment of mobile robot localization is designed to test the efficiency of the algorithm. In this experiment, the localization precision of robots can be improved almost 400% when visual protractor is introduced.