Incremental topological segmentation for semi-structured environments using discretized GVG

Abstract

Over the past few decades, topological segmentation has been much studied, especially for structured environments. In this work, we first propose a set of criteria to assess the quality of topological segmentation, especially for semi-structured environments in 2D. These criteria provide a general benchmark for different segmentation algorithms. Then we introduce an incremental approach to create topological segmentation for semi-structured environments. Our novel approach is based on spectral clustering of an incremental generalized Voronoi decomposition of discretized metric maps. It extracts sparse spatial information from the maps, and builds an environment model which aims at simplifying the navigation task for mobile robots. Experimental results in real environments show the robustness and the quality of the topological map created by the proposed method. Extended experiments for urban search and rescue missions are performed to show the global consistency of the proposed incremental segmentation method using six different trails, during which the test robot traveled 1.8 km in total.