Chongben Ni

The diverse nature of hull components in shipbuilding has created a demand for intelligent robots capable of performing various tasks without pre-teaching or template-based programming. Visual perception of a target’s outline is crucial for path planning in robotic edge grinding and other processes. Providing the target’s outline from point cloud or image data is essential for autonomous programming, requiring a high-performance algorithm to handle large amounts of data in real-time construction while preserving geometric details. The high computational cost of triangulation has hindered real-time industrial applications, prompting efforts to improve efficiency. To address this, a new improvement called Directive Searching has been proposed to enhance search efficiency by directing the search towards the target triangle cell and avoiding redundant searches. Another improvement, Heritable Initial, reduces the search amount by inheriting the start position from the last search. Combining Directive Searching and Heritable Initial into a new method called DSHI has led to a significant efficiency advancement, with a calculation efficiency improvement of nearly 300–3000 times compared to the ordinary Bowyer–Watson method. In terms of outlines extraction, DSHI has improved the extraction efficiency by 4–16 times compared to the ordinary Bowyer–Watson methods, while ensuring stable outlines results, and has also increased the extraction efficiency by 2–4 times compared to PCL. The DSHI method is also applied to actual ship component edge-grinding equipment, and its effect meets the shipbuilding process requirements. It could be inferred that the new method has potential applications in shipbuilding and other industries, offering satisfying efficiency and robustness for tasks such as automatic edge grinding.

The shipbuilding industry demands intelligent robot, which is capable of various tasks without laborious pre-teaching or programming. Vision system guided robots could be a solution for autonomous working. This paper introduces the principle and technique details of a vision system that guides welding robots in ship small assembly production. TOF sensors are employed to collect spatial points of workpieces. Huge data amount and complex topology bring great difficulty in the reconstruction of small assemblies. A new unsupervised line segment detector is proposed to reconstruct ship small assemblies from spatial points. Verified using data from actual manufacturing, the method of this paper demonstrated good robustness which is a great advantage for industrial applications. This paper’s work has been implemented in shipyards and shows good commercial potential. Intelligent, flexible industrial robots could be implemented with the findings of this study, which will push forward intelligent manufacturing in the shipbuilding industry.