On-line SLAM using clustered landmarks with omnidirectional vision

Abstract

The problem of SLAM (simultaneous localization and mapping) is a fundamental problem in autonomous robotics. It arises when a robot must create a map of the regions it has navigated while localizing itself on it, using results from one step to increase precision in another by eliminating errors inherent to the sensors. One common solution consists of establishing landmarks in the environment which are used as reference points for absolute localization estimates and form a sparse map that is iteratively refined as more information is obtained. This paper introduces a method of landmark selection and clustering in omnidirectional images for on-line SLAM, using the SIFT algorithm for initial feature extraction and assuming no prior knowledge of the environment. Visual sensors are an attractive way of collecting information from the environment, but tend to create an excessive amount of landmarks that are individually prone to false matches due to image noise and object similarities. By clustering several features in single objects, our approach eliminates landmarks that do not consistently represent the environment, decreasing computational cost and increasing the reliability of information incorporated. Tests conducted in real navigational situations show a significant improvement in performance without loss of quality.