Point cloud data map creation from factory design drawing for LiDAR localization of an autonomous mobile robot

When using an autonomous mobile robot, an environmental map should be created in advance. In this study, we propose a method for creating a point cloud data (PCD) map required for LiDAR localization in autonomous driving. The proposed method creates PCD maps from paper design drawings. For objects not depicted in the drawings, we introduce a tablet-scan, whose data are merged into the map created from the drawings. Three factors affecting the accuracy of self-localization are investigated during the map creation: the gap size in the PCD map, presence of the tablet-scan data, and random point alignment during the map creation. The effects of these factors on the localization accuracy are evaluated via simulations using actual scan data. Consequently, the existence of the optimal gap size and the accuracy enhancement using both the tablet-scan data and random point alignment are clarified. Moreover, autonomous driving using the PCD map created using the proposed method is successfully achieved.