Case-Based Reasoning Approaches to Robot Navigation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F03%3APU40931" target="_blank" >RIV/00216305:26210/03:PU40931 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Case-Based Reasoning Approaches to Robot Navigation

Popis výsledku v původním jazyce

In this paper we deal with possibilities of using case-based reasoning methods for improvement of autonomous robot navigation in a partially known dynamic environment. We describe CBR approaches to both levels of navigation, global and local, but the main attention is focused on a path planning problem. The aim is to help with the search of paths between two points without collisions with known and unknown obstacles. At the same time, minimizing the length, difficulty and risk of paths is needed. The ennvironment can be modeled by a two-dimensional grid or as a continuous space in which known obstacles and unattainable areas are defined. Verified paths are stored in a case base along with information about its properties. When proposing a path, first of all, the most similar already used paths are found. Then they are adapted to the new problem. When no sufficiently resembling paths are found, we use other methods for searching for the path (local search, genetic algorithms, etc.).

Název v anglickém jazyce

Case-Based Reasoning Approaches to Robot Navigation

Popis výsledku anglicky

In this paper we deal with possibilities of using case-based reasoning methods for improvement of autonomous robot navigation in a partially known dynamic environment. We describe CBR approaches to both levels of navigation, global and local, but the main attention is focused on a path planning problem. The aim is to help with the search of paths between two points without collisions with known and unknown obstacles. At the same time, minimizing the length, difficulty and risk of paths is needed. The ennvironment can be modeled by a two-dimensional grid or as a continuous space in which known obstacles and unattainable areas are defined. Verified paths are stored in a case base along with information about its properties. When proposing a path, first of all, the most similar already used paths are found. Then they are adapted to the new problem. When no sufficiently resembling paths are found, we use other methods for searching for the path (local search, genetic algorithms, etc.).

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2003

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 9th International Conference on Soft Computing MENDEL 2003

ISBN

80-214-2411-7

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

326-333

Název nakladatele

Brno University of Technology, Faculty of Mechanical Engineering

Místo vydání

Brno

Místo konání akce

Brno

Datum konání akce

4. 6. 2003

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—