A hierarchical approach to region division for mobile robot based on spectral cluster

This paper presents a hierarchical method of region division for mobile robot system based on spectral clustering algorithm. Firstly, to improve the exploration efficiency, topological map is constructed incrementally using a hybrid map model with grid-topplogy structure. And then, topology-based Voronoi Diagram is introduced to divide the map and express the whole environment uniquely. Meanwhile, Scale-Invariant Feature Transform (SIFT) feature is extracted to relate to different nodes, and RANdom SAmple Consensus (RANSAC) algorithm is integrated to optimize matching results. On this basis, an undirected weighted graph is built and the spectral clustering theory based on SIFT matching information is adopted to partition global topologycal map and realize region division. The paper details the architecture of the presented method and gives some experiments to verify the effectiveness.