Abstract
With the rapid advancement of robotic technology, traditional manufacturing industries are encountering unprecedented opportunities and challenges. The leather industry, as a typical representative, urgently requires automation. However, due to the irregular edges, softness, and variable shapes of leather, automation faces significant technical challenges. To address this issue, this study proposes a high-precision grasping point recognition model based on an improved PointNet++ algorithm. By incorporating the Shuffle Attention mechanism, the improved PointNet++ algorithm significantly enhances the capture of key features, improving the segmentation accuracy and overall performance of the leather grasping areas. Experimental results demonstrate that the improved model exhibits superior performance in leather recognition and grasping experiments, achieving a recognition success rate of 96% and a grasping success rate of 89.6%. These results fully validate the effectiveness and practicality of the improved model in handling leather, providing reliable technical support for automated leather processing.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call