拓扑地图中的房间检测

Room detection for topological maps

测绘是许多机器人应用的一个重要组成部分。为了评估测绘步骤的表现,需要对其得出的地图的质量进行衡量。地图对定位与路径规划而言都至关重要。本文以先前比较机器人所生成地图与基准地图的拓扑结构的尝试中已经使用的拓扑图匹配法为基础,采用Alpha Shape法对房间等地图开放区域的检测进行了扩展,通过在450幅由不同原始地图添加噪声后形成的地图上进行的充分测试,显示房间检测为匹配算法的稳定性与鲁棒性带来提升。

Mapping is an important part of many robotic applications. In order to measure the performance of the mappingprocess we have to measure the quality of its result： the map. The map is essential for robotic algorithms like localizationand path planning. In this paper ,based on the Topology Graph matching method which has been used in comparingthe topology of the robot generated map to the topology of a ground truth map, a novel algorithm with Alpha Shapeis applied to open areas＇ detection as an extension of the previous approach. On 450 maps which are generated by adding noise to different original maps, the experiments show the algorithm makes the matching method more stable and robust.