Deep Learning Based Online Semantic Mapping for Automated Guided Vehicles in Indoor Intralogistics Environments

This paper presents a semantic mapping system for mobile robots in intralogistics environments. The sensor data captured with a solid-state RGB-D LiDAR camera serves as input data for state-of-the-art deep learning based object recognition systems. The presented approach uses two deep learning algorithms, one for the 2D and one for the 3D space. The premier system YOLACT performs an instance segmentation on the RGB images. In an additional step, point clouds from the RGB-D sensor are converted into so called bird’s eye view images. The key idea is to feed these bird’s eye view images in combination with the prior knowledge generated by YOLACT into the latter system Complex-YOLO (CY) to obtain the spatial extension of the detected object. Moreover, a conventional Minimum Bounding Rectangle (MBR) approach is presented. Both approaches are evaluated by specific scenarios and selected metrics in combination with a highly precise motion capturing system, which provides ground truth data.