Indoor Path-Planning Algorithm for UAV-Based Contact Inspection

Indoor Visual-Based Localization System for Multi-Rotor UAVs

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 0.11 m, so not degrading when the aerial vehicle increases its altitude and, therefore, strongly improving similar state-of-the-art solutions.

Weakly Supervised Learning for Transmission Line Detection Using Unpaired Image-to-Image Translation

To achieve full autonomy of unmanned aerial vehicles (UAVs), obstacle detection and avoidance are indispensable parts of visual recognition systems. In particular, detecting transmission lines is an important topic due to the potential risk of accidents while operating at low altitude. Even though many studies have been conducted to detect transmission lines, there still remains many challenges due to their thin shapes in diverse backgrounds. Moreover, most previous methods require a significant level of human involvement to generate pixel-level ground truth data. In this paper, we propose a transmission line detection algorithm based on weakly supervised learning and unpaired image-to-image translation. The proposed algorithm only requires image-level labels, and a novel attention module, which is called parallel dilated attention (PDA), improves the detection accuracy by recalibrating channel importance based on the information from various receptive fields. Finally, we construct a refinement network based on unpaired image-to-image translation in order that the prediction map is guided to detect line-shaped objects. The proposed algorithm outperforms the state-of-the-art method by 2.74% in terms of F1-score, and experimental results demonstrate that the proposed method is effective for detecting transmission lines in both quantitative and qualitative aspects.

UAV Obstacle Avoidance Algorithm to Navigate in Dynamic Building Environments

In this work, a real-time collision avoidance algorithm was presented for autonomous navigation in the presence of fixed and moving obstacles in building environments. The current implementation is designed for autonomous navigation between waypoints of a predefined flight trajectory that would be performed by an UAV during tasks such as inspections or construction progress monitoring. It uses a simplified geometry generated from a point cloud of the scenario. In addition, it also employs information from 3D sensors to detect and position obstacles such as people or other UAVs, which are not registered in the original cloud. If an obstacle is detected, the algorithm estimates its motion and computes an evasion path considering the geometry of the environment. The method has been successfully tested in different scenarios, offering robust results in all avoidance maneuvers. Execution times were measured, demonstrating that the algorithm is computationally feasible to be implemented onboard an UAV.

Indoor Mapping of Magnetic Fields Using UAV Equipped with Fluxgate Magnetometer

Unmanned aerial vehicles (UAVs) are used nowadays in a wide range of applications, including monitoring, mapping, or surveying tasks, involving magnetic field mapping, mainly for geological and geophysical purposes. However, thanks to the integration of ultrasound-aided navigation used for indoor UAV flight planning and development in sensorics, the acquired magnetic field images can be further used, for example, to enhance indoor UAV navigation based on the physical quantities of the image or for the identification of risk areas in manufacturing or industrial halls, where workers can be exposed to high values of electromagnetic fields. The knowledge of the spatial distribution of magnetic fields can also provide valuable information from the perspective of the technical cleanliness. This paper presents results achieved with the original fluxgate magnetometer developed and specially modified for integration on the UAV. Since the magnetometer had a wider frequency range of measurement, up to 250 Hz, the DC (Direct Current) magnetic field and low frequency industrial components could be evaluated. From the obtained data, 3D magnetic field images using spline interpolation algorithms written in the Python programming language were created. The visualization of the measured magnetic field in the 3D plots offer an innovative view of the spatial distribution of the magnetic field in the area of interest.