The UJI Aerial Librarian Robot: A Quadcopter for Visual Library Inventory and Book Localisation

Abstract

Over time, the field of robotics has provided solutions to automate routine tasks in different scenarios. In particular, libraries are awakening great interest in automated tasks since they are semi-structured environments where machines coexist with humans and several repetitive operations could be automatically performed. In addition, multirotor aerial vehicles have become very popular in many applications over the past decade, however autonomous flight in confined spaces still presents a number of challenges and the use of small drones has not been reported as an automated inventory device within libraries. This paper presents the UJI aerial librarian robot that leverages computer vision techniques to autonomously self-localize and navigate in a library for automated inventory and book localization. A control strategy to navigate along the library bookcases is presented by using visual markers for self-localization during a visual inspection of bookshelves. An image-based book recognition technique is described that combines computer vision techniques to detect the tags on the book spines, followed by an optical character recognizer (OCR) to convert the book code on the tags into text. These data can be used for library inventory. Misplaced books can be automatically detected, and a particular book can be located within the library. Our quadrotor robot was tested in a real library with promising results. The problems encountered and limitation of the system are discussed, along with its relation to similar applications, such as automated inventory in warehouses.

3D Position Estimation of Objects for Inventory Management Automation Using Drones

“…Unlike previous studies using markers attached to shelves and grids [20], this paper proposes a novel framework for inventory management automation in all warehouses, including shelves and gridless warehouses. Furthermore, the proposed framework is available for the low-cost drone-mounted monocular camera, unlike previous studies using expensive RFID sensors [16,17].…”

“…Manjrekar et al [19] proposed a cost-friendly solution by using a drone that scans barcodes attached to products and stores product information in the database to regularly manage inventory in warehouses. Martinez et al [20] estimated the position of a drone using the ArUco marker attached to shelves for book inventory management. Radácsi et al [6] proposed an inventory management model using drones that is effective for exploring shelf systems structure of the warehouse.…”

“…Pan et al [33] proposed a 3D position estimation method based on the monocular camera using two QR codes from an image. Martinez et al [20] estimated 3D coordinates of remaining markers without 3D coordinates using 3D coordinates and images taken from multiple perspectives of initial markers. Furthermore, Kim et al [34] proposed position estimation of the camera using FIPs and alignment patterns of a single QR code.…”

Automatic Recognition Technology of Library Books Based on Convolutional Neural Network Model

“…Moreover, ART makes it easier to integrate libraries using other types of digital media, such as smartphones and internetbased catalogs. The scope and effect of library offerings are increased by this effortless integration, which enables readers to browse for, reserve, and utilize materials at libraries at any time or from any location [3]. A significant breakthrough in contemporary library administration is the Automated Identification Technologies of Public Literature, which gives institutions the chance to streamline activities, enhance customer service, and more.…”

QuadNet: A Hybrid Framework for Quadrotor Dead Reckoning

“…In [13][14][15] simultaneous localization and mapping (SLAM) approaches are used as an alternative to GNSS indoors. In [16], a quadrotor indoor navigation algorithm based on position-based visual servoing was suggested, while indoor quadrotor navigation based on visual markers for quadrotor position computation was used for library inventory and book localization was suggested in [17]. Both visual positioning systems and SLAM rely on a camera as a main sensor.…”