Self-Supervised Learning of Camera-based Drivable Surface Friction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00353565" target="_blank" >RIV/68407700:21230/21:00353565 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ITSC48978.2021.9564894" target="_blank" >http://dx.doi.org/10.1109/ITSC48978.2021.9564894</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ITSC48978.2021.9564894" target="_blank" >10.1109/ITSC48978.2021.9564894</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Self-Supervised Learning of Camera-based Drivable Surface Friction

Popis výsledku v původním jazyce

The visual predictor of a drivable surface friction ahead of the vehicle is presented. The image recognition neural network is trained in self-supervised fashion, as an alternative to tedious, error-prone, and subjective human annotation. The training images are labelled automatically by surface friction estimates from vehicle response during ordinary driving. The Unscented Kalman Filter algorithm is used to estimate tire-to-road interface friction parameters, taking into account the highly nonlinear nature of tire dynamics. Finally, the overall toolchain was validated using an experimental subscale platform and real-world driving scenarios. The resulting visual predictor was trained using about 3 000 images and validated on an unseen set of 800 test images, achieving 0.98 crosscorrelation between the visually predicted and the estimated value of surface friction.

Název v anglickém jazyce

Self-Supervised Learning of Camera-based Drivable Surface Friction

Popis výsledku anglicky

The visual predictor of a drivable surface friction ahead of the vehicle is presented. The image recognition neural network is trained in self-supervised fashion, as an alternative to tedious, error-prone, and subjective human annotation. The training images are labelled automatically by surface friction estimates from vehicle response during ordinary driving. The Unscented Kalman Filter algorithm is used to estimate tire-to-road interface friction parameters, taking into account the highly nonlinear nature of tire dynamics. Finally, the overall toolchain was validated using an experimental subscale platform and real-world driving scenarios. The resulting visual predictor was trained using about 3 000 images and validated on an unseen set of 800 test images, achieving 0.98 crosscorrelation between the visually predicted and the estimated value of surface friction.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

ITSC 2021: IEEE Conference on Intelligent Transportation Systems

ISBN

978-1-7281-9142-3

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

2773-2780

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Indianapolis

Datum konání akce

19. 9. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—