Online 3-D Modeling of Complex Workpieces for the Robotic Spray Painting With Low-Cost RGB-D Cameras

Abstract

The 3-D model of workpieces plays a significant role in robotic spray painting, which needs the geometry and shape information for painting-path planning or pose estimation. However, the models are rarely provided beforehand, even if they are available, random pose changes during workpiece conveying on the spray-painting pipeline also necessitates the usage of real-time 3-D reconstruction. In this case, we propose an online modeling approach for automatic spray-painting applications. Specifically, with two consumer RGB-D cameras mounted on the two sides of the pipeline, the data streams of the moving workpiece are continuously collected. Then, incorporating the 3-D contour feature and approximate linear motion characteristics of the workpiece, a modified iterative closest point (ICP) algorithm is proposed for fast registration of multiple workpiece point clouds with varying positions. Finally, based on the spatial distribution and point cloud quality evaluation, a joint weighted algorithm for fusing point clouds from different perspectives is proposed, which is effective for the issues of self-occlusion and has superior noise resistance. To estimate the system performance, an experimental platform was established to simulate the spray-painting production line. According to our experiments, the proposed method can completely model the complex workpieces with irregular polyhedral structure within 1500 ms, and the modeled geometry accuracy can reach less than 8 mm, which has a significant improvement compared with the conventional methods.