Custom Pallet Detection Using YOLOv5 Deep Learning Architecture

The development of warehouse 4.0 including automation system in warehousing can help operations and increase work efficiency. Autonomous forklift feature research in this study aims to be able to detect the presence of pallets, fork placement in pallet holes, and this research was conducted to contribute to building a perception system on forklifts that can work autonomously. The architecture of pallet detection is YOLOv5 (You Only Look Once) with several versions and certain levels of accuracy and prediction levels such as: YOLOv5N(Nano), YOLOv5S(Small), YOLOv5M (Medium), YOLOv5L (Large), YOLOv5X (Xtra -Large)