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.

Information-Fusion Methods Based Simultaneous Localization and Mapping for Robot Adapting to Search and Rescue Postdisaster Environments

“…A set of criteria are used to assess the quality of 2D topological map segmentation. Based on spectral clustering of an incremental generalized Voronoi decomposition of discretized metric maps, Liu et al [24] extracted sparse spatial information from the maps and built an environmental model which aims at simplifying exploration task for mobile robots; in [25] the ICP-based and the stereo-based T and R system on the respective data conducted offline processing.…”

Multi-robot target detection and tracking: taxonomy and survey

“…b) Discrete Worlds:: The discrete grid or tessellation models are widely used, as they straightforwardly define graphs, upon which algorithms exploiting graph theory can be built (Parsons, 1978;Megiddo et al, 1988;Derenick et al, 2009;Pasqualetti et al, 2010;Murrieta-Cid et al, 2007). However, it is difficult to transform a metrical model of the world into a meaningful topological model (Moors et al, 2005), and only few authors provide means to do so Kolling and Carpin, 2008;Liu et al, 2015): some directly assume that the graph is available, either handmade, or built by a prior process (Hollinger et al, 2009), others use random sampling as a compromise between the continuous world and a discrete model.…”

Cloud-Enhanced Robotic System for Smart City Crowd Control

“…Many tedious and potentially dangerous tasks are now possible avenues for deployment of robots because of their high endurance, speed, and precision. Tasks such as 3D path planning for search and rescue [1], navigation tasks [2], and 3D printing, along with scene recognition, scene analysis [3], and medical surgery [4] are examples of services being provided by the highly functional modern robot. Despite all the advancements of late, it is still infeasible to prepare individual robots with limitless capabilities.…”