New approaches for singularization in logistic applications using low cost 3D sensors
In this chapter, novel approaches for the detection of logistical objects (loading units) in the field of material flow applications are comparative presented, focusing on salut ions using low cast 3D sensors. These approaches realize substantial changes in comparison to traditional system design of logistic processes. Complex 3D-vision systems, costly laser scanners or throughput decreasing local sensor salut ions integrated in grippers are substituted by low cast Photonic Mixing Device (PMD) cameras or structured light sensors (like Asus Xtion or Microsoft Kinect). By using low cast sensors and modern point cloud processing algorithms for detection and classification in logistic applications like depalletizing, automation of usually manual processes will be economically feasible. Besides the description of different basic solution concepts for 2.5D and 3D, two practical applications are presented. Combining measurements of the PMD sensor and a predetermined model of loading situations, stored during the assembly of the pallet, is the first practical application for contour checking in the automated depalletizing process. This approach can compensate for the drawbacks of the comparatively low resolution of the PMD camera. Thus, it is possible to detect the deviation between the nominal and the actual loading positions and-if necessary-an automated correction of the packaging scheme may be initiated. A 3D scanning approach (with dynamic sensor positioning) to acquire a full, registered 3D model of the pallet load is explained within the second example. An essential part of both approaches are computer-graphics methods specific to the given problem. As a trans-applicable function, (auto) calibration techniques for 2.5 and 3D sensor applications will be presented. From an economic point of view, these approaches could decrease the costs of automated facility logistic processes. Within the evaluation the critical requirements to reach this aim are discussed on the application layer.