Regional topological segmentation based on mutual information graphs

When people communicate with robots, the most intuitive mean is by naming the different regions in the environment. The capability that robots are able to identify different regions highly depends on the unsupervised topological segmentation results. This paper addresses the problem of segmenting a metric map into regions. Nowadays many researches in this direction develop approaches based on spectral clustering. However there are inherent drawbacks of spectral clustering algorithms. In this paper, we first discuss these drawbacks using several testing results; then we propose our approach based on information theory which uses Chow-Liu tree to segment the composed graph according to the weight differences. The results show that our method provides more flexible and faster results in the sense of facilitating semantic mapping or further applications.