Employing Observation Angles in Pose Recognition; Application for Teach-and-Repeat Robot Navigation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00233253" target="_blank" >RIV/68407700:21230/15:00233253 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/15:00233253

Výsledek na webu

<a href="http://link.springer.com/chapter/10.1007%2F978-3-319-22383-4_12" target="_blank" >http://link.springer.com/chapter/10.1007%2F978-3-319-22383-4_12</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-22383-4_12" target="_blank" >10.1007/978-3-319-22383-4_12</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Employing Observation Angles in Pose Recognition; Application for Teach-and-Repeat Robot Navigation

Popis výsledku v původním jazyce

In this paper, a method is presented which uses landmark bearings to support navigation. The herein introduced approach expands on previous method that uses robust image features in conjunction with dead-reckoning to correct robot bearing. In the presented approach, a combination of omnidirectional camera, and exploiting the observation angles are used to address adjustment of positioning errors of the robot on the fly, without a need for dead-reckoning. This keeps the positioning deviation within specific bounds and thus avoids accumulative nature of dead-reckoning error. Although this information is insufficient for absolute triangulation, under certain constraints it proves satisfactory for direction estimation. Detecting the arrival at the previously learned location or comparing relative distance of the landmarks for each observation point is also possible. The presented approach was verified in simulation and on the real robot. Obtained results indicate the feasibility of the app

Název v anglickém jazyce

Employing Observation Angles in Pose Recognition; Application for Teach-and-Repeat Robot Navigation

Popis výsledku anglicky

In this paper, a method is presented which uses landmark bearings to support navigation. The herein introduced approach expands on previous method that uses robust image features in conjunction with dead-reckoning to correct robot bearing. In the presented approach, a combination of omnidirectional camera, and exploiting the observation angles are used to address adjustment of positioning errors of the robot on the fly, without a need for dead-reckoning. This keeps the positioning deviation within specific bounds and thus avoids accumulative nature of dead-reckoning error. Although this information is insufficient for absolute triangulation, under certain constraints it proves satisfactory for direction estimation. Detecting the arrival at the previously learned location or comparing relative distance of the landmarks for each observation point is also possible. The presented approach was verified in simulation and on the real robot. Obtained results indicate the feasibility of the app

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

Modelling and Simulation for Autonomous Systems (Second International Workshop, MESAS 2015)

ISBN

978-3-319-22382-7

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

8

Strana od-do

165-172

Název nakladatele

Springer International Publishing AG

Místo vydání

Cham

Místo konání akce

Praha

Datum konání akce

29. 4. 2015

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

000365044100012