WareVision: CNN Barcode Detection-Based UAV Trajectory Optimization for Autonomous Warehouse Stocktaking
Ivan Kalinov, Alexander Petrovsky, Valeriy Ilin, Egor Pristanskiy, Mikhail Kurenkov, Vladimir Ramzhaev, Ildar Idrisov, Dzmitry Tsetserukou
Abstract
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.
Topics & Concepts
BarcodeComputer scienceTrajectoryConvolutional neural networkArtificial intelligencePath (computing)Computer visionReal-time computingComputer networkOperating systemPhysicsAstronomyQR Code Applications and TechnologiesRobotics and Sensor-Based LocalizationRobotic Path Planning Algorithms