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.
Highlights
Robotics is mainly focused on the automation of repetitive and tedious tasks
With the aim to evaluate the performance of the developed system, first preliminary experiments were conducted at UJI Robotic Intelligence Laboratory in order to test the localization and navigation approach in which instead of books, the shelves contained a variety of ordinary objects (Figure 10)
Experiments were conducted outside opening hours due to the noise and propeller wash associated with the quadcopter in flight in the otherwise silent atmosphere of a library
Summary
Robotics is mainly focused on the automation of repetitive and tedious tasks. Since its beginnings, the main application domain was industrial settings due to their controlled nature. Compared with traditional wheeled robots, their main advantage is Sensors 2021, 21, 1079 their ability to move in three-dimensional space with little effort, flying at different altitudes and hovering in the target area to collect precise information This ability to move in 3D space, brings with it great scientific and technical challenges, specially in the case of autonomous flight in indoor spaces [32] for which perceptual intelligence based on aerial vision is called for to self-localize, navigate, and perform the desired tasks in human environments. Few such indoor systems exist, for instance, Harik et al [33] describe an approach combining an unmanned ground vehicle (UGV) and an UAV for the automation of warehouse inventory.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call