Adaptive Robotic Deburring of Molded Parts via 3D Vision and Tolerance-Constrained Non-Rigid Registration

This paper introduces an innovative automatic trajectory generation method for the robotic deburring of molded parts, effectively addressing challenges posed by burr defects and workpiece deformation common in casting and injection molding processes. Existing offline trajectory planning methods often struggle with substantial burr sizes and complex surface deformations, resulting in compromised machining quality due to over-adaptation. To overcome these issues, the proposed approach utilizes 3D vision techniques to achieve precise burr localization. A novel burr point cloud segmentation method based on feature analysis, combined with a tolerance-constrained non-rigid registration algorithm, accurately identifies burr regions and optimizes trajectory positioning within defined manufacturing tolerances. Furthermore, the method employs quantitative burr height distribution analysis to dynamically adjust robotic feed rates, significantly enhancing processing efficiency. Experimental validations demonstrated that the proposed method reduces the deburring time by up to 68% compared to conventional techniques, achieving an average trajectory deviation of only 0.79 mm. This study provides a robust, efficient, and precise solution for automating deburring operations in complex molded components, highlighting its substantial potential for industrial applications.