Affiliation:
1. The School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China
Abstract
In response to the problem of robots needing to perform bin-picking in many industries, a small robot system was developed with a workpiece-position-detection system based on Field-Programmable Gate Array (FPGA) technology. The system integrated object detection and feature matching techniques, bolstered by optimization methods, to enhance its functionality on the FPGA platform. Furthermore, a two-wire control bus was designed specifically for reliable operation in environments characterized by strong interference, drawing inspiration from the Controller Area Network (CAN) bus. The experimental results demonstrated that the system’s performance was comparable to that of the point-cloud-algorithm-based bin-picking system, while also exhibiting greater stability. Notably, the cost of the controller was significantly reduced, and the embedded hardware and software design ensured stability and adaptability for deployment in demanding settings, such as small-scale heavy industry factories.
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference24 articles.
1. Low-Cost, Real-Time Inspection of Oranges Using Machine Vision;Aleixos;IFAC Proc. Vol.,2000
2. Object Detection in 20 Years: A Survey;Zou;Proc. IEEE,2023
3. Redmon, J., and Angelova, A. (2015, January 26–30). Real-Time Grasp Detection Using Convolutional Neural Networks. Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA.
4. An Accurate and Robust Strip-Edge-Based Structured Light Means for Shiny Surface Micromeasurement in 3-D;Song;IEEE Trans. Ind. Electron.,2013
5. A New Integrated Robot Vision System from FANUC Robotics;Connolly;Ind. Robot. Int. J.,2007