Robust Autonomous Navigation of Unmanned Aerial Vehicles (UAVs) for Warehouses’ Inventory Application

Кwon, Wook Hyun; Park, Jun Ho; Lee, Minsu; Her, Jongbeom; Kim, Sang-Hyeon; Seo, Ja-Won

doi:10.1109/lra.2019.2955003

Cited by 80 publications

(49 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…5, three results are obtained for (t) i = 1 meter, 8i, 8t, shown in Fig. 6 From Fig. 6, it can be observed that the proposed algorithm performs well in the considered setting, given that its performance matches closely the path of the ground truth.…”

Section: A Simulation Environmentmentioning

confidence: 93%

GTRS-Based Algorithm for UAV Navigation in Indoor Environments Employing Range Measurements and Odometry

Matos-Carvalho¹,

Santos²,

Tomic³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

This work addresses the problem of unmanned aerial vehicle (UAV) navigation in indoor environments. Due to unavailability of satellite signals, the proposed algorithm takes advantage of terrestrial radio measurements between the UAV and a set of stationary reference points, from which it extracts range information, as well as odometry by means of inertial sensors, such as accelerometer. On the one hand, based on maximum a posteriori (MAP) criterion, the range information and accumulated knowledge throughout the UAV's movement are employed to derive a generalized trust region sub-problem (GTRS), that is solved exactly via bisection procedure. On the other hand, by using the UAV's transform in relation to the world, another position estimation is obtained by employing odometry. Finally, the two position estimates are combined through a Kalman filter (KF) to enhance the positioning accuracy and obtain the final UAV's position estimation. The UAV is then navigated to a desired destination, by simply calculating the velocity components in the shortest path. Our results show that the proposed algorithm is robust to various model parameters for high precision (HP) UAV sensors, achieving reasonably good positioning accuracy. Besides, the results corroborate that the proposed algorithm is suitable for real-time applications, consuming (on average) only 21 ms to estimate the UAV position.INDEX TERMS Generalized trust region sub-problem (GTRS), indoor environments, Kalman filter (KF), maximum a posteriori (MAP) estimator, navigation, odometry, positioning, unmanned aerial vehicle (UAV).

show abstract

Section: A Simulation Environmentmentioning

confidence: 93%

GTRS-Based Algorithm for UAV Navigation in Indoor Environments Employing Range Measurements and Odometry

Matos-Carvalho¹,

Santos²,

Tomic³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…So far, we focused on one bookcase since this is where the real novelty is for automated book inventory and localization using aerial vision. Moving within the aisles of a regular structure has already been addressed in the literature [ 41 ], this is a common behavior whenever a drone has to fly along the aisles limited by sets of racks or walls. To this end, apart for moving to a specific point at a bookcase, a behavior to move to a point outside a bookcase, along with a transition between the bookcases, and a plan to visit the bookcases one after the other in a predefined sequence, need to be in place.…”

Section: Navigationmentioning

confidence: 99%

“…For their part, Han et al [ 40 ] proposed to use topological maps although they get a high accuracy, the processing does not work in real-time, making it inappropriate for our goal. An extended Kalman filter (EKF)-based multi-sensor fusion framework was used in [ 41 ] and in this case, a simple map consisting of pose information of attached tags is the base of a warehouse inventory application. Another common solution for UAV navigation is the use of landmarks.…”

Section: Introductionmentioning

confidence: 99%

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

Martínez-Martín

Ferrer

Vasilev

et al. 2021

Sensors

View full text Add to dashboard Cite

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.

show abstract

“…The need for automated inventory management solutions was recently increased to replace current manual methods [ 47 ]. UAVs were used in Reference [ 48 ] for inventory inspection at indoor warehouses to increase the efficiency of cost and time, as well as the safety of human workers. A low-cost sensing system was developed with an EKF-based multi-sensor fusion framework for autonomous navigation of UAVs in warehouse indoor environments.…”

Section: Indoor Positioning Of Unmanned Air Vehicles (Uavs)mentioning

confidence: 99%

Particle Filtering for Three-Dimensional TDoA-Based Positioning Using Four Anchor Nodes

Khalaf-Allah

2020

Sensors

View full text Add to dashboard Cite

In this article, the four-anchor time difference of arrival (TDoA)-based three-dimensional (3D) positioning by particle filtering is addressed. The implemented particle filter uses 1000 particles to represent the probability density function (pdf) of interest, i.e., the posterior pdf of the target node’s state (position). A resampling procedure is used to generate particles in the prediction step, and TDoA measurements are used to determine the importance, i.e., weight, of each particle to enable updating the posterior pdf and estimating the position of the target node. The simulation results show the feasibility of this approach and the possibility to employ it in indoor positioning applications under the assumed working conditions using, e.g., the ultra-wideband (UWB) wireless technology. Therefore, it is possible to enable unmanned air vehicle (UAV) positioning applications, e.g., inventory management in large warehouses, without the need for an excessive number of anchor nodes.

show abstract

Robust Autonomous Navigation of Unmanned Aerial Vehicles (UAVs) for Warehouses’ Inventory Application

Cited by 80 publications

References 8 publications

GTRS-Based Algorithm for UAV Navigation in Indoor Environments Employing Range Measurements and Odometry

GTRS-Based Algorithm for UAV Navigation in Indoor Environments Employing Range Measurements and Odometry

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

Particle Filtering for Three-Dimensional TDoA-Based Positioning Using Four Anchor Nodes

Contact Info

Product

Resources

About