Hybrid Vision-Based Navigation for Mobile Robots in Mixed Indoor/Outdoor Environments

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00223349" target="_blank" >RIV/68407700:21230/15:00223349 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.patrec.2014.10.010" target="_blank" >http://dx.doi.org/10.1016/j.patrec.2014.10.010</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.patrec.2014.10.010" target="_blank" >10.1016/j.patrec.2014.10.010</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Hybrid Vision-Based Navigation for Mobile Robots in Mixed Indoor/Outdoor Environments

Popis výsledku v původním jazyce

In this paper we present a vision-based navigation system for mobile robots equipped with a single, off-the-shelf camera in mixed indoor/outdoor environments. A hybrid approach is proposed, based on the teach-and-replay technique, which combines a path-following and a feature-based navigation algorithm. We describe the navigation algorithms and show that both of them correct the robot's lateral displacement from the intended path. After that, we claim that even though neither of the methods explicitly estimates the robot position, the heading corrections themselves keep the robot position error bound. We show that combination of the methods outperforms the pure feature-based approach in terms of localization precision and that this combination reducesmap size and simplifies the learning phase. Experiments in mixed indoor/outdoor environments were carried out with a wheeled and a tracked mobile robots in order to demonstrate the validity and the benefits of the hybrid approach.

Název v anglickém jazyce

Hybrid Vision-Based Navigation for Mobile Robots in Mixed Indoor/Outdoor Environments

Popis výsledku anglicky

In this paper we present a vision-based navigation system for mobile robots equipped with a single, off-the-shelf camera in mixed indoor/outdoor environments. A hybrid approach is proposed, based on the teach-and-replay technique, which combines a path-following and a feature-based navigation algorithm. We describe the navigation algorithms and show that both of them correct the robot's lateral displacement from the intended path. After that, we claim that even though neither of the methods explicitly estimates the robot position, the heading corrections themselves keep the robot position error bound. We show that combination of the methods outperforms the pure feature-based approach in terms of localization precision and that this combination reducesmap size and simplifies the learning phase. Experiments in mixed indoor/outdoor environments were carried out with a wheeled and a tracked mobile robots in order to demonstrate the validity and the benefits of the hybrid approach.

Druh

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

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/7AMB14AR015" target="_blank" >7AMB14AR015: Multi-robotické autonomní systémy</a><br>

Návaznosti

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

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název periodika

Pattern Recognition Letters

ISSN

0167-8655

e-ISSN

—

Svazek periodika

53

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

11

Strana od-do

118-128

Kód UT WoS článku

000349555500017

EID výsledku v databázi Scopus

2-s2.0-84922541097