Research and Design of Motion Control System Based on Visual Navigation AGV

Chuhao Weng

doi:10.54097/4ts0b336

Authors

Chuhao Weng

DOI:

https://doi.org/10.54097/4ts0b336

Keywords:

Automated guided vehicles, Manual markers, Visual positioning, Fuzzy PID control.

Abstract

Automated Guided Vehicles (AGVs) have emerged as a crucial element of intelligent logistics and automated warehousing systems, with enormous potential for a variety of uses, thanks to the quick development of manufacturing and logistics. Given its advantages over other AGV navigation techniques—such as precise location, inexpensive hardware costs, and flexible routing—visual navigation has drawn more attention from researchers. This article examines the visual navigation of AGVs' motion control system within the framework of a smart manufacturing workshop. In this study, the AGV motion control system's general design is described. The algorithm for visual placement is designed and presented second. The study then looks into a fuzzy PID control self-tuning technique. AGV path-tracking error models are created, and MATLAB simulation is used to compare fuzzy PID and traditional PID models and show the advantages and disadvantages of each control technique. The motion control system's functional implementation is finally covered. The external device interface circuits are constructed, and the hardware platform is chosen using the high-performance multi-core video processor, TMS320DM8148. The software architecture of the motion control system is built, and the development of the visual positioning and path-tracking algorithms, along with other functional modules, is finished, all while utilizing the performance benefits of ARM and DSP processors.

Downloads

Download data is not yet available.

References

[1] Le-Anh T, De Koster M B M. A review of design and control of automated guided vehicle systems. European Journal of Operational Research, 2005,171 (1):1-23.

[2] Hwang H, Moon S, Gen M. An integrated model for designing an end-of-aisle order picking system and determining of unit load sizes of AGVs. Computers & Industrial Engineering, 2002, 42 (2): pp249-258.

[3] Feng Yongli. Research on control technology of visually guided AGV. Hebei United University, 2014.

[4] Waxman, A., Moigne, et al. A visual navigation system. IEEE Journal on Robotics and Automation.1986, 42 (2): 249-258.

[5] Waxman, A., Moigne, et al. Visual navigation of roadways. IEEE International Conference on Robotics and Automation. 1985, 1985: 862-867.

[6] Pomerleau, D. RALPH: rapidly adapting lateral position handler. IEEE Intelligent Vehicles Symposium (IV '95). 1995, 1995: 506-511.

[7] Baluja S. Evolution of an artificial neural network based autonomous land vehicle controller. IEEE transactions on systems, man, and cybernetics, Part B. Cybernetics: A publication of the IEEE Systems, Man, and Cybernetics Society, 1996,26 (3): 450-463.

[8] Gatesichapakorn S. et al. ROS based autonomous mobile robot navigation using 2D LiDAR and RGB-D Camera: 2019 First International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP), Bangkok, Thailand, Thailand, 2019, 2019:151-154.

[9] Wang Yu. Research on positioning technology and path planning based on visual navigation AGV. Virtual Reality & Intelligent Hardware. Anhui University, 2019, 5 (3): 249-265.

[10] Zheng Shaohua. Research on positioning and path planning technology of visual navigation AGV. South China University of Technology, 2016.

[11] Zheng Haiyan. Optimization Algorithm for PID Control Parameters of Electrical Equipment in Rural Electric Drainage and Irrigation Stations. Mobile Information Systems. 2022, 2022: 1-12.

[12] Si Bingyu. Research on several issues of autonomous robot navigation based on visual artificial landmarks. Northeastern University, 2003.