Semantic Segmentation Based Spraying Trajectory Planning for Complex Product

Trajectory planning is a fundamental step for robotic spraying. This article proposes a semantic segmentation based spraying trajectory planning method for complex products. In order to divide the complex product surface into different painting regions, a geometric feature guided segmentation network (GFGS-Net) is developed. In the GFGS-Net, a geometric local encoding module is constructed to capture edge points based on the proposed local geometric feature, then encode the geometric feature and semantic feature of spraying surface. An attentive feature augmentation module is further designed to adaptively reweight and concatenate the encoded geometric feature and encoded semantic feature. With the aid of such feature representation, GFGS-Net can better describe the industrial product surface and perform accurate product surface segmentation. Afterwards, different spraying patterns are designed for each region, and key spraying parameters spraying overlap distance and spray gun speed are optimized considering the paint thickness and spraying time. Based on these two aspects, the spraying trajectory can be generated through point cloud slicing followed by alpha-shapes and intercept reduction. Alpha-shapes is used to obtain the contour lines of complex product surface, and the contour lines is further smoothed by intercept reduction to make the painting robot work more smoothly. The experiment results demonstrate that the proposed method can significantly improve painting quality and efficiency for complex products.