Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 2

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
The market for unmanned aerial vehicles (UAVs), along with their associated applications and services, has been developing at a rapid pace in recent years. One of the key emerging trends is the use of UAV swarms, which enable the execution of complex tasks more efficiently than single platforms. Effective control of such a swarm, whether by a human operator or autonomously, requires maintaining safe distances between individual UAVs. This, in turn, necessitates precise navigation and mutual localization within the swarm, posing both technical and operational challenges. This paper presents a comprehensive review of recent advancements in relative localization techniques within UAV swarms. With the increasing interest in UAV swarm applications for tasks such as search and rescue, surveillance, and delivery, accurate and reliable localization methods have become critical for maintaining formation and avoiding collisions. The paper categorizes localization approaches into cooperative methods and autonomous sensing and further classifies them by the type of sensor used: optical, radio frequency, and acoustic. For each category, representative technologies, and algorithms, such as ultra-wideband (UWB), received signal strength indication (RSSI), angle of arrival (AOA), multidimensional scaling (MDS), and convolutional neural network (CNN)-based vision systems, are discussed, along with their strengths, limitations, and suitability for Global Positioning System (GPS)-denied environments. The paper concludes with an identification of current research gaps, including the challenges of sensor array integration on UAV platforms and the influence of environmental interference on localization accuracy.
PL
W niniejszej pracy zaproponowano i przetestowano system wizyjny służący śledzeniu lecącej piłki w celu wypracowania sterowania dla robota wieloosiowego mającego za zadanie złapanie jej. Do detekcji i lokalizacji piłki na obrazie z dwóch, prostopadle ustawionych, kamer zastosowano laplasjan filtru gaussowskiego (LoG) oraz autorski podsystem filtracji rozmytej. Estymację trajektorii lecącej piłki w przestrzeni wykonano w oparciu o metodę najmniejszych kwadratów z wykorzystaniem funkcji liniowej i kwadratowej. Zamieszczono szczegółowy opis proponowanego rozwiązania oraz wyniki przeprowadzonych testów.
EN
In the paper, a vision system for tracking a flying ball was proposed and tested, aiming at developing a control mechanism for a multi-axis robot designed to catch it. To detect and locate the ball in the image from two perpendicularly positioned cameras, a Laplacian of a Gaussian filter (LoG) and a custom fuzzy filtering subsystem were used. The trajectory of a flying ball in space was estimated based on the least squares method using a linear and square function. A detailed description of the proposed solution and the results of the tests performed are included.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.