Automated Classification Platform with SCARA Robot and Artificial Vision

Farfán Manrique A.; Ojeda Villalta G.; Rojas Zevallos G.; Tejada Villanueva E.; Quispe Ccachuco M.; Mestas Ramos S. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2025) · DOI: 10.18687/laccei2025.1.1.544

Resumen

The automation of industrial processes has given rise to innovative solutions that combine robotics and artificial vision to optimize the sorting of parts. In this context, the development of a SCARA robot capable of selecting and sorting parts using an artificial vision system based on an ESP32 as the main camera is presented. After analyzing the images, the SCARA robot controller executes precise trajectories that allow parts to be sorted according to predefined criteria. This type of approach ensures efficient and repetitive handling, optimizing operation times in production lines. The mechanical structure of the SCARA has been designed to offer high speed and accuracy, essential characteristics in industrial environments where reliability is a priority. The ESP32 as a camera offers good resolution, a powerful processor, and high connectivity, making it a compact and cost-effective solution that facilitates its implementation in applications where cost reduction is essential. Additionally, an intuitive graphical interface was designed, allowing the user to configure classification parameters and monitor system performance in real time, enhancing its flexibility and adaptability. This proposal integrates areas such as computer vision, robotic control, and mechatronic design, standing out for its ability to efficiently solve complex tasks, as well as for its functionality and accessibility. In this way, the prototype is consolidated as a practical and versatile tool for automated piece classification. This work demonstrates the potential of accessible technologies in developing advanced solutions for the industry, positioning the system as a promising alternative in the field of industrial automation.

Instituciones: Universidad Católica de Santa María