A Spray Path Planning Algorithm based on 3D Point Cloud

Abstract

Robotic spray path planning for complex surface has always been a challenging problem, especially when it comes to flexible manufacturing system. This paper presents a new method to plan the spray path based on the point cloud obtained by vision sensors. In order to select the direction of slice adaptively, a method based on principal component analysis (PCA) is adopted to calculate the dominant eigenvector of point cloud. The intersection algorithm is also discussed to obtain points for constructing spraying path. The normal vector calculation and sorting problem of slice points are also solved. The experimental results show that the proposed path planning method can automatically generate the spraying path according to the surface of spray target. This method can also be extended to other applications.