Improving perception and locomotion capabilities of mobile robots in urban search and rescue missions - PhD Thesis Proposal

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00301601" target="_blank" >RIV/68407700:21230/16:00301601 - isvavai.cz</a>

Výsledek na webu

<a href="http://cmp.felk.cvut.cz/pub/cmp/articles/kubelka/Kubelka-TR-2016-02.pdf" target="_blank" >http://cmp.felk.cvut.cz/pub/cmp/articles/kubelka/Kubelka-TR-2016-02.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Improving perception and locomotion capabilities of mobile robots in urban search and rescue missions - PhD Thesis Proposal

Popis výsledku v původním jazyce

Localization of mobile robots is an important topic, especially in Urban Search & Rescue (USAR) scenarios. Information about position and orientation of the robot serves not only to human operators but it is also necessary for higher-level functions of the robot. We provide overview of the state-of-the-art localization techniques and present our solution for a mobile USAR robotic platform that incorporates various internal (proprioceptive) and external (exteroceptive) measurements to exploit their complementary character. We show that when available, exteroceptive sensor modalities greatly improve performance of the localization. However, we also demonstrate that there are situations (e.g. low visibility) where the standard localization algorithms fail and which require different approach. We propose to exploit tactile and proprioceptive information to create a model of terrain the robot traverses. Our goal is to utilize the model to substitute for missing information normally provided by the exteroceptive sensors. If successful, we can improve localization and therefore locomotion capability of the robot in such scenarios.

Název v anglickém jazyce

Improving perception and locomotion capabilities of mobile robots in urban search and rescue missions - PhD Thesis Proposal

Popis výsledku anglicky

Localization of mobile robots is an important topic, especially in Urban Search & Rescue (USAR) scenarios. Information about position and orientation of the robot serves not only to human operators but it is also necessary for higher-level functions of the robot. We provide overview of the state-of-the-art localization techniques and present our solution for a mobile USAR robotic platform that incorporates various internal (proprioceptive) and external (exteroceptive) measurements to exploit their complementary character. We show that when available, exteroceptive sensor modalities greatly improve performance of the localization. However, we also demonstrate that there are situations (e.g. low visibility) where the standard localization algorithms fail and which require different approach. We propose to exploit tactile and proprioceptive information to create a model of terrain the robot traverses. Our goal is to utilize the model to substitute for missing information normally provided by the exteroceptive sensors. If successful, we can improve localization and therefore locomotion capability of the robot in such scenarios.

Druh

V_souhrn - Souhrnná výzkumná zpráva

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Počet stran výsledku

28

Místo vydání

Praha

Název nakladatele resp. objednatele

Center for Machine Perception, K13133 FEE Czech Technical University

Verze

—