UAV Autonomous Localization Using Macro-Features Matching with a CAD Model

Abstract

Research in the field of autonomous Unmanned Aerial Vehicles (UAVs) has significantly advanced in recent years, mainly due to their relevance in a large variety of commercial, industrial, and military applications. However, UAV navigation in GPS-denied environments continues to be a challenging problem that has been tackled in recent research through sensor-based approaches. This paper presents a novel offline, portable, real-time in-door UAV localization technique that relies on macro-feature detection and matching. The proposed system leverages the support of machine learning, traditional computer vision techniques, and pre-existing knowledge of the environment. The main contribution of this work is the real-time creation of a macro-feature description vector from the UAV captured images which are simultaneously matched with an offline pre-existing vector from a Computer-Aided Design (CAD) model. This results in a quick UAV localization within the CAD model. The effectiveness and accuracy of the proposed system were evaluated through simulations and experimental prototype implementation. Final results reveal the algorithm's low computational burden as well as its ease of deployment in GPS-denied environments.

Comprehensive Investigation of Unmanned Aerial Vehicles (UAVs): An In-Depth Analysis of Avionics Systems

“…The localization of a UAV is the process of determining its position in a given environment, involving the obtainment of accurate information about the UAV's spatial coordinates (i.e., latitude, longitude, orientation, etc.). In relation to other navigation hierarchies (e.g., path planning), it enables a precise execution of the planned paths and strategies [141][142][143][144][145]. Concerning vision-based UAV localization techniques, they can be characterized according to two main sets as follows: Relative Visual Localization (RVL) [146,147] and Absolute Visual Localization (AVL) [148].…”

Unmanned aerial vehicle navigation in underground structure inspection: A review

“…UAVs can only navigate through partial information when their flight path is simple. In a tunnel with a basically unchanged environment, UAV map creation can adopt various forms of prior information (Haque et al, 2020). The drone needs to sense and map as conditions change in the tunnel.…”

Simulation of Mechanical NC Machining Based on CAD/CAM

“…Today, with the gradual development of science and technology, any high-cost scientific and technological research activities are inseparable from the simulation system to ensure the rigor and correctness of scientific research results. With the development of simulation technology, the simulation industry has become a new type of industry with considerable scale [17].…”