Industrial Environment Mapping Using Distributed Static 3D Sensor Nodes

Abstract

This paper presents a system architecture for mapping and real-time monitoring of a relatively large industrial robotic environment of size 10 m × 15 m × 5 m. Six sensor nodes with embedded computing power and local processing of the 3D point clouds are placed close to the ceiling. The system architecture and data processing is based on the Robot Operating System (ROS) and the Point Cloud Library (PCL). The 3D sensors used are the Microsoft Kinect for Xbox One and point cloud data is collected at 20 Hz. A new manual calibration procedure is developed using reflective planes. The specified range of the used sensor is 0.8 m to 4.2 m, while depth data up to 9 m is used in this paper. Despite the fact that only six sensors are used and that the Kinect sensors are operated beyond the specified range, a benchmark of the accuracy compared with a Leica laser distance meter demonstrates an accuracy of 10 mm or better in the final 3D point cloud.