elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Contact | Deutsch
Fontsize: [-] Text [+]

Automatic Maneuver Recognition in the Automobile: the Fusion of Uncertain Sensor Values using Bayesian Models

Gerdes, Arati (2006) Automatic Maneuver Recognition in the Automobile: the Fusion of Uncertain Sensor Values using Bayesian Models. In: Proceedings of the 3rd International Workshop on Intelligent Transportation (WIT 2006), pp. 129-133. 3rd International Workshop on Intelligent Transportation (WIT 2006), 2006-03-14 - 2006-03-15, Hamburg, Deutschland.

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
210kB
[img] MS PowerPoint
2MB

Abstract

A probabilistic system for automatic driving maneuver recognition from CAN-Bus and sensor data is in development at the German Aerospace Center (DLR). Major obstacles to automatic maneuver recognition in the automobile today are presented by the wide variety of styles in which driving maneuvers are performed and the high degree of uncertainty present in the sensor data. Traditional rule-based systems are ill-equipped to deal with these problems. Instead, Bayesian models, which offer a solid, theoretical framework for the derivation of inferences from uncertain evidence, are used for the inference of the driving maneuver being performed. Driver behavior analysis and tests of a prototype maneuver-recognition system are performed in real traffic using the ViewCar, a research vehicle equipped with cameras and sensors to measure and record CAN-Bus, environment and driver data. Experiments with the prototype system yield a driving maneuver recognition rate of approximately 92%.

Document Type:Conference or Workshop Item (Speech, Paper)
Title:Automatic Maneuver Recognition in the Automobile: the Fusion of Uncertain Sensor Values using Bayesian Models
Authors:
AuthorsInstitution or Email of Authors
Gerdes, AratiUNSPECIFIED
Date:24 January 2006
Journal or Publication Title:Proceedings of the 3rd International Workshop on Intelligent Transportation (WIT 2006)
Refereed publication:Yes
In ISI Web of Science:No
Page Range:pp. 129-133
Status:Published
Keywords:Bayesian Networks, probabilistic methods, driving maneuver recognition
Event Title:3rd International Workshop on Intelligent Transportation (WIT 2006)
Event Location:Hamburg, Deutschland
Event Type:international Conference
Event Dates:2006-03-14 - 2006-03-15
Organizer:Hamburg University of Technology
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:V SH - Verbesserung der Sicherheit im Verkehr (old)
DLR - Research area:Transport
DLR - Program:V SH - Verbesserung der Sicherheit im Verkehr
DLR - Research theme (Project):V - Entwicklung Fahrermodell (old)
Location: Braunschweig
Institutes and Institutions:Institute of Transportation Systems > Institute of Transportation Systems > Automotive
Deposited By: Arati Gerdes
Deposited On:20 Mar 2006
Last Modified:12 Dec 2013 20:10

Repository Staff Only: item control page

Browse
Search
Help & Contact
Informationen
electronic library is running on EPrints 3.3.12
Copyright © 2008-2012 German Aerospace Center (DLR). All rights reserved.