Anordnung und Verfahren zur Vorhersage der Strassenreibung in einem Strassennetz

Details

Veröffentlichungs-Nr.

EP3206411

Aktenzeichen

EP16155263

Anmeldetag

11. Februar 2016

Veröffentlichung

7. Oktober 2020

Erteilung

7. Oktober 2020

Rechtsraum

EP

IPC

G01N33/42H04Q9/00G08G1/01

Abstract

A system and method for predicting road friction using data (D<1>-D<n>) from a fleet of connected vehicles (V<1-n>). Each fleet vehicle comprises a communication arrangement (4) for reporting, to a back end system (5), floating car data sets (D<1>-D<n>), including a position of the vehicle, time data and data regarding determined road friction influencing parameters and a determined road friction associated with that position (P<1>-P<n>). The data sets (D<1>-D<n>) are collected and aggregated in a central database (6), over a predetermined time period. A neural network computer (7) is trained and validated, using the aggregated data sets (D<1>-D<n>), to create a model to predict future road friction for a specific road network (3) position (P<1>-P<n>) or segment associated with that specific position (P<1>-P<n>). Once trained and validated, the neural network computer (7) will, upon receiving the same type of new, up to date, input data, use the model to predict future road friction for such a specific position (P<1>-P<n>) or segment of the road network (3).

Anmelder

Firma

Volvo Car Corporation

Land

🇸🇪 Schweden

Fachgebiete