Performance Analysis of Localization Algorithms for Inspections in 2D and 3D Unstructured Environments Using 3D Laser Sensors and UAVs

One of the most relevant problems related to Unmanned Aerial Vehicle’s (UAV) autonomous navigation for industrial inspection is localization or pose estimation relative to significant elements of the environment. This paper analyzes two different approaches in this regard, focusing on its application to unstructured scenarios where objects of considerable size are present, such as a truck, a wind tower, an airplane, a building, etc. The presented methods require a previously developed Computer-Aided Design (CAD) model of the main object to be inspected. The first approach is based on an occupancy map built from a horizontal projection of this CAD model and the Adaptive Monte Carlo Localization (AMCL) algorithm to reach convergence by considering the likelihood field observation model between the 2D projection of 3D sensor data and the created map. The second approach uses a point cloud prior map of the 3D CAD model and a scan-matching algorithm based on the Iterative Closest Point Algorithm (ICP) and the Unscented Kalman Filter (UKF). The presented approaches have been extensively evaluated using simulated as well as previously recorded real flight data. We focus on aircraft inspection as a test example, but our results and conclusions can be directly extended to other applications. To support this assertion, a truck inspection has been performed. Our tests reflected that creating a 2D or 3D map from a standard CAD model and using a 3D laser scan on the created maps can optimize the processing time, resources and improve robustness. The techniques used to segment unexpected objects in 2D maps improved the performance of AMCL. In addition, we showed that moving around locations with relevant geometry after take-off when running AMCL enabled faster convergence and high accuracy. Hence, it could be used as an initial position estimation method for other localization algorithms. The ICP-NL method works well in environments with elements other than the object to inspect, but it can provide better results if some techniques to segment the new objects are applied. Furthermore, the proposed ICP-NL scan-matching method together with UKF performed faster, in a more robust manner, than NDT. Moreover, it is not affected by flight height. However, ICP-NL error may still be too high for applications requiring increased accuracy.

Machine learning techniques in internet of UAVs for smart cities applications

Recently, there were much interest in technology which has emerged greatly to the development of smart unmanned systems. Internet of UAV (IoUAV) enables an unmanned aerial vehicle (UAV) to connect with public network, and cooperate with the neighboring environment. It also enables UAV to argument information and gather data about others UAV and infrastructures. Applications related to smart UAV and IoUAV systems are facing many impairments issues. The challenges are related to UAV cloud network, big data processing, energy efficiency in IoUAV, and efficient communication between a large amount of different UAV types, in addition to optimum decisions for intelligence. Artificial Intelligence (AI) technologies such as Machine Learning (ML) mechanisms enable to archives intelligent behavior for unmanned systems. Moreover, it provides a smart solution to enhance IoUAV network efficiency. Decisions in data processing are considered one of the most problematic issues related to UAV especially for the operations related to cloud and fog based network levels. ML enables to resolve some of these issues and optimize the Quality of UAV network experience (QoE). The paper provides theoretical fundamentals for ML models and algorithms for IoUAV applications and recently related works, in addition to future trends.