Exploration and Mapping Technique Suited for Visual-features Based Localization of MAVs

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F16%3A00242515" target="_blank" >RIV/68407700:21730/16:00242515 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/16:00242515

Výsledek na webu

<a href="http://link.springer.com/article/10.1007%2Fs10846-016-0358-8" target="_blank" >http://link.springer.com/article/10.1007%2Fs10846-016-0358-8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10846-016-0358-8" target="_blank" >10.1007/s10846-016-0358-8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Exploration and Mapping Technique Suited for Visual-features Based Localization of MAVs

Popis výsledku v původním jazyce

An approach for long term localization, stabilization, and navigation of micro-aerial vehicles (MAVs) in unknown environment is presented in this paper. The proposed method relies strictly on onboard sensors of employed MAVs and does not require any external positioning system. The core of the method consists in extraction of information from pictures consequently captured using a camera carried by the particular MAV. Visual features are obtained from images of the surface under the MAV, and stored into a map that is represented by these features. The position of the MAV is then obtained through matching with previously stored features. An important part of the proposed system is a novel approach for exploration and mapping of the workspace of robots. This method enables efficient exploring of the unknown environment, while keeping the iteratively built map of features consistent. The proposed algorithm is suitable for mapping of surfaces, both outdoor and indoor, with various density of the image features. The sufficient precision and long term persistence of the method allows its utilization for stabilization of large MAV groups that work in formations with small relative distances between particular vehicles. Numerous experiments with quadrotor helicopters and various numerical simulations have been realized for verification of the entire system and its components.

Název v anglickém jazyce

Exploration and Mapping Technique Suited for Visual-features Based Localization of MAVs

Popis výsledku anglicky

An approach for long term localization, stabilization, and navigation of micro-aerial vehicles (MAVs) in unknown environment is presented in this paper. The proposed method relies strictly on onboard sensors of employed MAVs and does not require any external positioning system. The core of the method consists in extraction of information from pictures consequently captured using a camera carried by the particular MAV. Visual features are obtained from images of the surface under the MAV, and stored into a map that is represented by these features. The position of the MAV is then obtained through matching with previously stored features. An important part of the proposed system is a novel approach for exploration and mapping of the workspace of robots. This method enables efficient exploring of the unknown environment, while keeping the iteratively built map of features consistent. The proposed algorithm is suitable for mapping of surfaces, both outdoor and indoor, with various density of the image features. The sufficient precision and long term persistence of the method allows its utilization for stabilization of large MAV groups that work in formations with small relative distances between particular vehicles. Numerous experiments with quadrotor helicopters and various numerical simulations have been realized for verification of the entire system and its components.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of Intelligent and Robotic Systems

ISSN

0921-0296

e-ISSN

—

Svazek periodika

84

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

19

Strana od-do

351-369

Kód UT WoS článku

000390027900022

EID výsledku v databázi Scopus

2-s2.0-84961116993