Terrain Learning Using Time Series of Ground Unit Traversal Cost

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00342303" target="_blank" >RIV/68407700:21230/20:00342303 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-43890-6_8" target="_blank" >https://doi.org/10.1007/978-3-030-43890-6_8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-43890-6_8" target="_blank" >10.1007/978-3-030-43890-6_8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Terrain Learning Using Time Series of Ground Unit Traversal Cost

Popis výsledku v původním jazyce

In this paper, we concern learning of terrain types based on the traversal experience observed by a hexapod walking robot. The addressed problem is motivated by the navigation of unmanned ground vehicles in long-term autonomous missions in a priory unknown environments such as extraterrestrial exploration. In such deployments, the robotic vehicle needs to learn hard to traverse terrains to improve its autonomous performance and avoid possibly dangerous areas. We propose to utilize Growing Neural Gas for terrain learning to capture the robot experience with traversing the terrain and thus learn a classifier of individual terrain types. The classifier is learned using a real time-series dataset collected by a hexapod walking robot traversing various terrain types. The learned model can be utilized to predict the traversal cost of newly observed terrains to support decisions on where to navigate next.

Název v anglickém jazyce

Terrain Learning Using Time Series of Ground Unit Traversal Cost

Popis výsledku anglicky

In this paper, we concern learning of terrain types based on the traversal experience observed by a hexapod walking robot. The addressed problem is motivated by the navigation of unmanned ground vehicles in long-term autonomous missions in a priory unknown environments such as extraterrestrial exploration. In such deployments, the robotic vehicle needs to learn hard to traverse terrains to improve its autonomous performance and avoid possibly dangerous areas. We propose to utilize Growing Neural Gas for terrain learning to capture the robot experience with traversing the terrain and thus learn a classifier of individual terrain types. The classifier is learned using a real time-series dataset collected by a hexapod walking robot traversing various terrain types. The learned model can be utilized to predict the traversal cost of newly observed terrains to support decisions on where to navigate next.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

6th International Workshop on Modelling and Simulation for Autonomous Systems

ISBN

9783030438890

ISSN

—

e-ISSN

1611-3349

Počet stran výsledku

11

Strana od-do

97-107

Název nakladatele

Springer

Místo vydání

Wien

Místo konání akce

Palermo

Datum konání akce

29. 10. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000628847000008