WareVision: CNN Barcode Detection-Based UAV Trajectory Optimization for Autonomous Warehouse Stocktaking

摘要

This letter presents a heterogeneous Unmanned Aerial Vehicle (UAV)-based robotic system for real-time barcode detection and scanning using Convolutional Neural Networks (CNN). The proposed approach improves the UAV's localization using scanned barcodes as landmarks in a real warehouse with low-light conditions. Instead of using the standard overlapping snake-based grid (OSBG) trajectory, we implement a novel approach for flight-path optimization based on barcode locations. This approach reduces the time of warehouse stocktaking and decreases the number of mistakes in barcode scanning.