Deep Transfer Learning of Traversability Assessment for Heterogeneous Robots

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00364546" target="_blank" >RIV/68407700:21230/22:00364546 - isvavai.cz</a>

Výsledek na webu

<a href="https://ceur-ws.org/Vol-3226/paper1.pdf" target="_blank" >https://ceur-ws.org/Vol-3226/paper1.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Deep Transfer Learning of Traversability Assessment for Heterogeneous Robots

Popis výsledku v původním jazyce

For autonomous robots operating in an unknown environment, it is important to assess the traversability of the surrounding terrain to improve path planning and decision-making on where to navigate next in a cost-efficient way. Specifically, in mobile robot exploration, terrains and their traversability are unknown prior to the deployment. The robot needs to use its limited resources to learn its terrain traversability model on the go; however, reusing a provided model is still a desirable option. In a team of heterogeneous robots, the models assessing traversability cannot be reused directly since robots might possess different morphology or sensory equipment and thus experience the terrain differently. In this paper, we propose a transfer learning approach for convolutional neural networks assessing the traversability between heterogeneous robots, where the transferred network is retrained using data available for the target robot to accommodate itself to the robot’s traversability. The proposed method is verified in real-world experiments, where the proposed approach provides faster learning convergence and better traversal cost predictions than the baseline.

Název v anglickém jazyce

Deep Transfer Learning of Traversability Assessment for Heterogeneous Robots

Popis výsledku anglicky

For autonomous robots operating in an unknown environment, it is important to assess the traversability of the surrounding terrain to improve path planning and decision-making on where to navigate next in a cost-efficient way. Specifically, in mobile robot exploration, terrains and their traversability are unknown prior to the deployment. The robot needs to use its limited resources to learn its terrain traversability model on the go; however, reusing a provided model is still a desirable option. In a team of heterogeneous robots, the models assessing traversability cannot be reused directly since robots might possess different morphology or sensory equipment and thus experience the terrain differently. In this paper, we propose a transfer learning approach for convolutional neural networks assessing the traversability between heterogeneous robots, where the transferred network is retrained using data available for the target robot to accommodate itself to the robot’s traversability. The proposed method is verified in real-world experiments, where the proposed approach provides faster learning convergence and better traversal cost predictions than the baseline.

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/GC21-33041J" target="_blank" >GC21-33041J: Učení plánování pohybu ve složitých úlohách</a><br>

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 22nd Conference Information Technologies – Applications and Theory (ITAT 2022)

ISBN

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

9

Strana od-do

12-20

Název nakladatele

CEUR Workshop Proceedings

Místo vydání

Aachen

Místo konání akce

Zuberec

Datum konání akce

23. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—