Tracking Robotic Arms with YOLO11 for Smart Automation in Industry 4.0

Abstract

The rapid advancement of automation and robotics has become a cornerstone of the smart industry and Industry 4.0, necessitating innovative approaches to enhance operational efficiency and accuracy. In this context, computer vision plays a vital role in monitoring robotic systems, ensuring they perform tasks with precision and reliability. This study employs the YOLO11 algorithm to track the end effector of a robotic arm during pick-and-place operations, simulating industrial environments. Through rigorous experimentation, we observed that YOLO11 demonstrated a high tracking performance, achieving average detection metrics that indicate a strong correlation between commanded and experimental trajectories. The findings highlight that the algorithm can maintain a tracking accuracy above 90%, even during varying movement speeds, thereby reducing the likelihood of operational errors. This research underscores the significance of integrating advanced deep learning techniques into robotic systems, paving the way for enhanced automation capabilities within the framework of Industry 4.0.