3D Vision-Guided Robotic Grinding Framework for Repairing Random Defects

Robotic grinding is utilized for machining large complex components due to its exceptional flexibility and expansive workspace. However, the existing research primarily focuses on the global machining and lacks solutions for repair and remanufacturing of components with local defects. In order to perform the local repair efficiently, this paper proposes a 3D vision-guided robotic grinding framework for repairing random defects, by taking the removal of welding slags on the automotive body as an example. Based on the measured point cloud, a robust function weighted variance minimization (RFWVM) registration algorithm is utilized to position the automotive body with high precision. Meanwhile, the datum plane is reconstructed to extract the defect point clouds. On this basis, the welding slags are divided into regions in accordance with their height characteristics. For these regions, a robotic grinding depth prediction model is then constructed to determine the mapping between welding slag height and process parameters, and the genetic algorithm is further improved to solve the shortest path decision-making problem in robotic grinding. The experimental results conducted in a typical region of an automotive body confirm the practicality and effectiveness of the proposed framework. This study provides a valuable reference for local defects repair of complex components. Note to Practitioners—This work is motivated by local repair and remanufacturing in robotic machining of large complex components. Due to the random positions and sizes of local defects, it is highly challenging for robots to perform efficient and high-quality machining of these localized defects. The framework proposed in this paper is implemented based on high-precision 3D vision,which can realize the positioning of the workpiece and defect extraction simultaneously. The shortest machining path is determined using intelligent optimization algorithms, while the developed grinding depth prediction model assigns specific machining parameters to each defect area, ensuring both high-quality and efficiency machining. This framework can also be adapted for the removal of similar random defects, such as putty defects and paint defects on high-speed train bodies. However, it has certain limitations. For example, the approach is not suitable for machining small components using robots, does not offer advantages in conventional fixed-point global machining scenarios, and may face measurement challenges when machining workpieces that surface with numerous bends, which requires further improvement.