Robot arm grasping based on YOLOv5 in the perspective of automated production

Abstract The rapid development of industrial intelligence has gradually expanded the application of automated production. As a typical automated production equipment, the robotic arm still faces the problems of low grasping efficiency and high control costs when facing highly integrated and miniaturized components. Given this, to improve the grasping level of the robotic arm in complex production environments, this study first constructs a kinematic mathematical model of the robotic arm. Secondly, based on the algorithm that You Only Look Once, improvements are made to its convolution operation and feature extraction modules, ultimately proposing a new type of robotic arm grasping control model. The results showed that the loss test value of the new model was the lowest at 2.75, the average detection error of the captured object was the lowest at 0.003, and the average detection time was the shortest at 1.28 seconds. The highest success rate for grasping six types of industrial parts was 94%, and the lowest average energy consumption was 35.67 joules. Therefore, research models can significantly improve the grasping performance of robotic arms under various complex conditions, thereby achieving efficient manipulation of robotic arms in industrial automation.