ABSTRACT
Liu, X.; Hu, Y., and Xiao, C.-S., 2019. A new robust and fast iterative closest point algorithm for 3D Ship Hull Plate Bending Machines. In: Gong, D.; Zhu, H., and Liu, R. (eds.), Selected Topics in Coastal Research: Engineering, Industry, Economy, and Sustainable Development. Journal of Coastal Research, Special Issue No. 94, pp. 264–268. Coconut Creek (Florida), ISSN 0749-0208.
The registration accuracy has a direct impact on the processing accuracy of sheet metal in 3D Ship Hull Plate Bending Machines. This study introduces a new distance measure, Root-Mean-Squared iterative closest point (RMS-ICP) algorithm to significantly improve the robustness of the algorithm, and reduce the influence of outliers. At the same time, the 3D point sets registration algorithm is optimized. In addition, the RMS-ICP has been optimized in robustness, registration accuracy and convergence speed in comparison with the original ICP and other improved ICP algorithms. The experiment results support that the performance of the RMS-ICP algorithm is better than other methods. Overall, the RMS-ICP algorithm is very effective in dealing with the point sets registration problem in 3D Ship Hull Plate Bending Machine.
