Local environment recognition based on multi-sensor data fusion

As autonomous robot, possessing visual and range information acquisition capability is very crucial to explore unknown environments reliably, SIFT (Scale Invariant Feature Transform) algorithm is a powerful tool in detecting objects under various imaging conditions, robot can use the recognized object as landmarks to navigate and localize itself. The laser scanning data is not sensitive to noise and lightness of the environment, most of the robots use laser rangefinder for its navigation and localization. This paper presents a method to recognize local environment based on data fusion, experimental results demonstrate the effectiveness of the proposed algorithm.