Indoor Visual-Based Localization System for Multi-Rotor UAVs

Abstract

Industry 4.0, smart homes, and the Internet of Things are boosting the employment of autonomous aerial vehicles in indoor environments, where localization is still challenging, especially in the case of close and cluttered areas. In this paper, we propose a Visual Inertial Odometry localization method based on fiducial markers. Our approach enables multi-rotor aerial vehicle navigation in indoor environments and tackles the most challenging aspects of image-based indoor localization. In particular, we focus on a proper and continuous pose estimation, working from take-off to landing, at several different flying altitudes. With this aim, we designed a map of fiducial markers that produces results that are both dense and heterogeneous. Narrowly placed tags lead to minimal information loss during rapid aerial movements while four different classes of marker size provide consistency when the camera zooms in or out according to the vehicle distance from the ground. We have validated our approach by comparing the output of the localization algorithm with the ground-truth information collected through an optoelectronic motion capture system, using two different platforms in different flying conditions. The results show that error mean and standard deviation can remain constantly lower than 0,11m, so not degrading when the aerial vehicle increases its altitude and, therefore, strongly improving similar state-of-the-art solutions.

Dört rotorlu bir insansız hava aracının görüntü tabanlı otomatik kontrolü ve hedef takibi

“…Nitekim pozisyon ölçümünde kullanılan sensörlerden kaynaklanan kontrol algoritmalarına bozucu girdilerinin etkilerini en aza indirmek ve hedefe ait öznitelikleri çıkartabilmek için görüntü momentlerinden yararlanılabilmektedir [16,17]. Görüntü düzleminden öznitelik çıkarımlarıyla elde edilen veriler iç ve dış döngü kontrolcüleri tarafından kullanılmaktadır [18,19]. Hedef hareketine bağlı olarak istenen takip açıları dış döngü kontrolcüsü tarafından hesaplanırken, yönelim komutları iç döngü kontrolcüsü tarafından uygulanmaktadır.…”

Analytical Models for Pose Estimate Variance of Planar Fiducial Markers for Mobile Robot Localisation

“…In articles using the EKF, it is common that data from the motion sensor are typically included in the prediction step, while the pose estimate from the markers is used in the correction step. However, the type of sensors used in the EKF prediction model and the type of markers may differ from article to article; for example, Zeng et al [ 36 ] used encoders, in [ 10 , 11 , 18 ] IMU is used, while in [ 37 ] Chavez et al used the combination of IMU and Doppler velocity log (DVL). The correct setting of the observation noise covariance matrix is also essential for the proper function of the Kalman filter.…”

“…Chavez et al used as matrix entries the standard deviation of pose estimates from several markers, while Zheng et al adjusted the entries proportionally to the estimated distance and angle of view of the markers. In [ 10 , 11 , 18 ], there is little information on how the authors have addressed this issue.…”

“…Passive fiducial markers come in different spatial dimensions, shapes and sizes. For mobile robotics, planar quadrilateral markers (e.g., ArUco [ 9 ], AprilTag, ARTag) are among the most commonly used variants described in [ 10 , 11 ]. These markers are monochromatic, and the information is encoded in n-by-n internal pixels that are surrounded by a frame designed to help distinguish them from their surroundings and used to estimate the position of the marker relative to the camera.…”

Evaluation of Safe Landing Site Detection Methods for Unmanned Aerial Vehicles

“…There is a variety of ways to find a safe landing area. Indoor environment GPS signals are weak, so UAVs must require some helpful system in this indoor landing situation [37]. Using different methods, a UAV will look for safe landing areas.…”