Automatic Loading and Unloading System with Workpiece Identification Based on YOLOv5.

In the production process, the workpiece must be mounted and fixed on the machine tool before the machine tool performs various processes on the part’s surface. After the process, the workpiece is removed and placed in the corresponding area. In this paper, a robotic, automatic loading and unloading system for small workpieces is designed for machine tools’ automatic loading and unloading. In order to find workpieces in the system, a YOLO-based workpiece object detection algorithm is used to obtain information about the type and location of workpieces in the automatic loading and unloading process. For the problems arising from the experiments, the $$\alpha $$ -IOU loss function is used to replace the GIOU loss function in the original network. The experimental results show that $$\alpha $$ -IOU significantly improves object detection accuracy compared to GIOU.