Fuzzy geometric maps and vertex self-localization for SLAM problem
SLAM问题中的模糊几何地图与顶点自定位法

This paper proposes a vertex self-localization method based on fuzzy geometric maps to solve the real-time localization of in-door SLAM (simultaneously localization and map building) problem. The vertex self-localization is to extract the vertexes of polygons as the landmarks from the raw sensor information. Compared with the traditional edge match method, vertex self-localization has higher accuracy and less computational complexity. A novel twice-classification method is also proposed to improve the precision of digital maps. Finally, experimental results are given to show that our method is more efficient than the traditional edge match method.