Video based localization for Bertha

Author

Ziegler, Jens ; Lategahn, Henning ; Schreiber, Markus ; Keller, Christoph G. ; Knoppel, Carsten ; Hipp, Jochen ; Haueis, Martin ; Stiller, Christoph

Author_Institution

Dept. on Mobile Perception Syst., FZI Res. Center for Inf. Technol., Karlsruhe, Germany

fYear

2014

fDate

8-11 June 2014

Firstpage

1231

Lastpage

1238

Abstract

In August 2013, the modified Mercedes-Benz SClass S500 Intelligent Drive (“Bertha”) completed the historic Bertha-Benz-Memorial-Route fully autonomously. The self-driving 103 km journey passed through urban and rural areas. The system used detailed geometric maps to supplement its online perception systems. A map based approach is only feasible if a precise, map relative localization is provided. The purpose of this paper is to give a survey on this corner stone of the system architecture. Two supplementary vision based localization methods have been developed. One of them is based on the detection of lane markings and similar road elements, the other exploits descriptors for point shaped features. A final filter step combines both estimates while handling out-of-sequence measurements correctly.

Keywords

artificial intelligence; automobiles; computer vision; mobile robots; object detection; Bertha-Benz-Memorial-Route; Mercedes-Benz SClass S500 Intelligent Drive; geometric maps; lane marking detection; online perception systems; point shaped features; road elements; self-driving; system architecture; video based localization; vision based localization methods; Cameras; Feature extraction; Geometry; Global Positioning System; Sensors; Trajectory; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicles Symposium Proceedings, 2014 IEEE

Conference_Location

Dearborn, MI

Type

conf

DOI

10.1109/IVS.2014.6856560

Filename

6856560