Traversability Transfer Learning Between Robots with Different Cost Assessment Policies

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00359490" target="_blank" >RIV/68407700:21230/22:00359490 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-98260-7_21" target="_blank" >https://doi.org/10.1007/978-3-030-98260-7_21</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-98260-7_21" target="_blank" >10.1007/978-3-030-98260-7_21</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Traversability Transfer Learning Between Robots with Different Cost Assessment Policies

Popis výsledku v původním jazyce

Predicting mobile robots' traversability over terrains is crucial to select safe and efficient paths through rough and unstructured environments. In multi-robot missions, knowledge transfer techniques can enable learning terrain traversability assessment the robots did not experience individually. The knowledge can be incrementally aggregated for homogeneous robots since they can treat foreign knowledge as their own. However, robots with different perceptions might experience the same terrain differently, so it is impossible to aggregate the shared knowledge directly. In this paper, we show how to learn a model that transfers the experience between heterogeneous robots, enabling each robot to use the whole sum of the experience of the multi-robot team. The proposed approach uses correlation to combine individual neural networks that assess the traversability of individual robots. The presented method has been verified in a real-world deployment of multi-legged walking robots with different cost assessment policies.

Název v anglickém jazyce

Traversability Transfer Learning Between Robots with Different Cost Assessment Policies

Popis výsledku anglicky

Predicting mobile robots' traversability over terrains is crucial to select safe and efficient paths through rough and unstructured environments. In multi-robot missions, knowledge transfer techniques can enable learning terrain traversability assessment the robots did not experience individually. The knowledge can be incrementally aggregated for homogeneous robots since they can treat foreign knowledge as their own. However, robots with different perceptions might experience the same terrain differently, so it is impossible to aggregate the shared knowledge directly. In this paper, we show how to learn a model that transfers the experience between heterogeneous robots, enabling each robot to use the whole sum of the experience of the multi-robot team. The proposed approach uses correlation to combine individual neural networks that assess the traversability of individual robots. The presented method has been verified in a real-world deployment of multi-legged walking robots with different cost assessment policies.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

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

Modelling and Simulation for Autonomus Systems

ISBN

978-3-030-98259-1

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

12

Strana od-do

333-344

Název nakladatele

Springer-Verlag

Místo vydání

Berlin

Místo konání akce

Virtual

Datum konání akce

20. 10. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000787774900021