Optimizing Bayesian networks for recognition of driving maneuvers to meet the automotive requirements

Author

Weidl, Galia ; Madsen, Anders L. ; Kasper, Dietmar ; Breuel, Gabi

Author_Institution

R&D, Dept. of Driving Autom., Daimler AG, Böblingen, Germany

fYear

2014

fDate

8-10 Oct. 2014

Firstpage

1626

Lastpage

1631

Abstract

An Object Oriented Bayesian Network for recognition of maneuver in highway traffic has demonstrated an acceptably high recognition performance on a prototype car with a Linux PC having an i7 processor. This paper is focusing on keeping the high recognition performance of the original OOBN, while evaluating alternative modelling techniques and their impact on the memory and time requirements of an ECU-processor for automotive applications. New challenges are faced, when the prediction horizon is to be further extended.

Keywords

Linux; automotive engineering; belief networks; driver information systems; object-oriented programming; Bayesian networks; ECU-processor; Linux PC; OOBN; alternative modelling techniques; automotive application; automotive requirements; driving maneuver recognition; highway traffic; i7 processor; object oriented Bayesian network; prediction horizon; prototype car; recognition performance; Computational modeling; Hidden Markov models; Memory management; Object oriented modeling; Random access memory; Uncertainty; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control (ISIC), 2014 IEEE International Symposium on

Conference_Location

Juan Les Pins

Type

conf

DOI

10.1109/ISIC.2014.6967630

Filename

6967630