Using ADASIS Version 3 data to improve localization for highly auto-mated driving

Konferenz: AmE 2019 – Automotive meets Electronics - 10. GMM-Fachtagung
12.03.2019 - 13.03.2019 in Dortmund, Deutschland

Tagungsband: GMM-Fb. 93: AmE 2019

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Ohl, Sebastian; Koska, Olav (Elektrobit Automotive GmbH, Erlangen, Germany)

A major prerequisite for highly automated driving systems using high definition map data is the knowledge about the vehicle's position. This position needs to have a much higher precision than it can be achieved with a GNSS sensor alone. Therefore, various other sensor systems, like gyroscopes or odometers, can be used to enhance the position estimation. This contribution describes a system using another input, ADASISv3 map data, to improve the positioning. The map data is received from a map database and then compared to traffic sign measurements from a camera system. The comparison results are used to enhance the vehicle's position. The system has been evaluated with a test vehicle in real world situations. A description of the scenario and test results are included in the contribution.