Perception, Planning and Control System for Automated Slalom with Porsche Panamera

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F21%3A00353430" target="_blank" >RIV/68407700:21730/21:00353430 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.46720/F2020-ACM-064" target="_blank" >https://doi.org/10.46720/F2020-ACM-064</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.46720/F2020-ACM-064" target="_blank" >10.46720/F2020-ACM-064</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Perception, Planning and Control System for Automated Slalom with Porsche Panamera

Popis výsledku v původním jazyce

Automation of various driving tasks is an important aspect of today’s car industry. Not requiring drivers to simultaneously concentrate on several tasks can lead to increased safety. Carmakers use automation to improve quality and reproducibility of car testing, independently on particular driver. In this paper, we focus on automation of one test scenario performed by carmakers – a slalom drive. We present hardware and software architecture that allows a stock Porsche Panamera car to drive automatically through a slalom track formed by traffic cones. Our solution relies on few additional sensors like a differential GPS, a camera, and a 16-layer LiDAR. Our control algorithms run on the NVIDIA TX2 platform and are integrated using Robotic Operating System (ROS) middleware. The perception layer detects cones in camera images using a Support Vector Machine and Histogram of Oriented Gradients feature vectors. Interfacing with the car Electronic Control Units (ECUs) is made via CAN and FlexRay buses. We validate our system in experiments with a real car.

Název v anglickém jazyce

Perception, Planning and Control System for Automated Slalom with Porsche Panamera

Popis výsledku anglicky

Automation of various driving tasks is an important aspect of today’s car industry. Not requiring drivers to simultaneously concentrate on several tasks can lead to increased safety. Carmakers use automation to improve quality and reproducibility of car testing, independently on particular driver. In this paper, we focus on automation of one test scenario performed by carmakers – a slalom drive. We present hardware and software architecture that allows a stock Porsche Panamera car to drive automatically through a slalom track formed by traffic cones. Our solution relies on few additional sensors like a differential GPS, a camera, and a 16-layer LiDAR. Our control algorithms run on the NVIDIA TX2 platform and are integrated using Robotic Operating System (ROS) middleware. The perception layer detects cones in camera images using a Support Vector Machine and Histogram of Oriented Gradients feature vectors. Interfacing with the car Electronic Control Units (ECUs) is made via CAN and FlexRay buses. We validate our system in experiments with a real car.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/8A19011" target="_blank" >8A19011: Arrowhead Tools for Engineering of Digitalisation Solutions</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the FISITA 2021 World Congress

ISBN

978-1-9160259-2-9

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

—

Název nakladatele

FISITA - International Federation of Automotive Engineering Societies

Místo vydání

London

Místo konání akce

Praha

Datum konání akce

14. 9. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—