Laser Scanned Real Environment for Intelligent Virtualization of Crane Lifting

Abstract

BackgroundThis paper presents a Tower Crane Intelligent Lifting Path Planner (TCILP) for the lifting task in the environments which are highly complex. The environment can be old industrial plants existing over many decades, or sites with tentative storage spaces. Often, these environments do not have workable digital models or are impractical to have 3D representations are impractical. MethodsThe current investigation introduces the cutting-edge technology of laser scanning to convert the real environments into point cloud format regarded as the virtualized version of the construction sites or plants. The challenge is to deal with the huge data set of point clouds of multiple scans in order to produce a complete virtualized model. The tower crane is also virtualized for the path planning purpose. A parallelized Genetic Algorithm is employed to address the intelligent path planning issue for the lifting task of tower cranes in complicated environments taking the advantage of Graphics Processing Unit technology, which has high computing performance yet low cost. ResultsOptimal lifting paths are generated in several seconds.