Fisheye-Based Smart Control System for Autonomous UAV Operation

Abstract

Recently, as UAVs (unmanned aerial vehicles) have become smaller and higher-performance, they play a very important role in the Internet of Things (IoT). Especially, UAVs are currently used not only in military fields but also in various private sectors such as IT, agriculture, logistics, construction, etc. The range is further expected to increase. Drone-related techniques need to evolve along with this change. In particular, there is a need for the development of an autonomous system in which a drone can determine and accomplish its mission even in the absence of remote control from a GCS (Ground Control Station). Responding to such requirements, there have been various studies and algorithms developed for autonomous flight systems. Especially, many ML-based (Machine-Learning-based) methods have been proposed for autonomous path finding. Unlike other studies, the proposed mechanism could enable autonomous drone path finding over a large target area without size limitations, one of the challenges of ML-based autonomous flight or driving in the real world. Specifically, we devised Multi-Layer HVIN (Hierarchical VIN) methods that increase the area applicable to autonomous flight by overlaying multiple layers. To further improve this, we developed Fisheye HVIN, which applied an adaptive map compression ratio according to the drone’s location. We also built an autonomous flight training and verification platform. Through the proposed simulation platform, it is possible to train ML-based path planning algorithms in a realistic environment that takes into account the physical characteristics of UAV movements.

Military Applications of Machine Learning: A Bibliometric Perspective

“…In general terms, it can be said that the data that predominate in the military context are more complex to process than those in a conventional organization. In the study we have carried out, the main sources found are biometric data, e.g., from electroencephalograms [70]; data from military experts and commanders (e.g., field assessments and weaponry needed in that particular field), which should be used in conjunction with the other data to build decision systems [35]; the Internet of things, smart and connected devices widely used by the military, generating large volumes of information over time [71], e.g., those provided by radars [72]; the Internet of battlefield things, which connects soldiers with smart technology in weapons and other objects to give troops "extra sensory powers" [73]; military personnel data, e.g., those obtained in screening interviews [74]; military veterans' data obtained, e.g., from their administrative personal files [75]; and other data, both internal and open in any format (including videos, images and speeches), e.g., those coming from unmanned aerial vehicles [76], videos for facial recognition [77,78], data from the Internet, etc. ; -Insight generation for military.…”

Smart Search System of Autonomous Flight UAVs for Disaster Rescue

“…However, traditional VIN-based algorithms cannot cover a wide area. Thus, in this paper, we adopted a hierarchical VIN [22] method for path planning to cover a large target area such as our test fields (4 km × 4 km and 1 km × 1 km).…”

Estimating the distance to an object from grayscale stereo images using deep learning

“…In recent years, we have seen rapid development in the field of autonomous vehicles. Scientists are conducting intensive research on vehicle autonomy in various environments: water [1,2], ground [3][4][5][6], and air [7][8][9][10]. The vast majority of vehicle autonomy is based on meters and sensors.…”