Abstract
In this research, we present an intelligent forklift cargo precision transfer system to address the issue of poor pallet docking accuracy and low recognition rate when using current techniques. The technology is primarily used to automatically check if there is any pallet that need to be transported. The intelligent forklift is then sent to the area of the target pallet after being recognized. Images of the pallets are then collected using the forklift’s camera, and a deep learning-based recognition algorithm is used to calculate the precise position of the pallets. Finally, the forklift is controlled by a high-precision control algorithm to insert the pallet in the exact location. This system creatively introduces the small target detection into the pallet target recognition system, which greatly improves the recognition rate of the system. The application of Yolov5 into the pallet positional calculation makes the coverage and recognition accuracy of the algorithm improved. In comparison with the prior approach, this system’s identification rate and accuracy are substantially higher, and it requires fewer sensors and indications to help with deployment. We have collected a significant amount of real data in order to confirm the system’s viability and stability. Among them, the accuracy of pallet docking is evaluated 1000 times, and the inaccuracy is kept to a maximum of 6 mm. The recognition rate of pallet recognition is above 99.5% in 7 days of continuous trials.
Funder
Zhejiang Province Science and Technology Plan Project
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference33 articles.
1. Coordinating hundreds of cooperative, autonomous vehicles in warehouses;Wurman;AI Mag.,2008
2. Guest editorial: A revolution in the warehouse: A retrospective on kiva systems and the grand challenges ahead;D’Andrea;IEEE Trans. Autom. Sci. Eng.,2012
3. Gadd, M., and Newman, P. A framework for infrastructure-free warehouse navigation. Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), 2015.
4. Wu, C.H., Tsang, Y.P., Lee, C.K.M., and Ching, W.K. A Blockchain-IoT Platform for the Smart Pallet Pooling Management. Sensors, 2021. 21.
5. Motroni, A., Buffi, A., Nepa, P., Pesi, M., and Congi, A. An Action Classification Method for Forklift Monitoring in Industry 4.0 Scenarios. Sensors, 2021. 21.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Optimized Pallet Localization Using RGB-D Camera and Deep Learning Models;2023 IEEE 19th International Conference on Intelligent Computer Communication and Processing (ICCP);2023-10-26
2. Efficient Intelligence with Applications in Embedded Sensing;Sensors;2023-05-17