Cooperative Cars - CoCar

The Cooperative Cars (CoCar) project and its successor CoCarX, funded by the German Federal Ministry for Research and Education, investigated the suitability of UMTS technologies and their foreseeable extensions (LTE) for direct, targeted transmission of traffic data arising from both stationary and vehicle-based sensors. The CoCar project is a part of the research initiative Adaptive and Cooperative Technologies for the Intelligent Traffic (AKTIV) led by the German automotive industry. Five partners from telecommunications and automobile industry identified which traffic management and driver assistance applications are suitable for use of this technology.

Informatik 5 cooperated in this project with Ericsson in Aachen and Fraunhofer FIT and develop data models, algorithms and systems for the data management of cooperative vehicle applications. One focus is the research on a data quality model to simulate and estimate the effect of various parameters in data acquisition and processing for traffic state estimation and forecasting. Furthermore, we investigate data stream management systems as the core component for the data management, and we study data stream mining algorithms for the traffic state estimation. Also data quality monitoring during the whole data management process is an important aspect we implemented in the framework.

Demonstration Video - Queue-end Detection

At the CoCarX final presentation in Düsseldorf (see also http://dbis.rwth-aachen.de/cms/news/chairnews.2011-06-14.6672946615) we presented the video below demonstrating our work on the framework including the data stream management system GSN (Global Sensor Network) and the data stream mining framework MOA (Massive Online Analysis). We utilized the traffic simulation software VISSIM to simulate the vehicles, to generate the Cooperative Car messages, and to visualize the scenarios. This work has been supported by the German Federal Ministry for Research and Education (BMBF) and is part of the research initiative aktiv. Especially, we like to thank for their support: Ericsson, PTV AG, and Stefan Schiffer (Knowledge-Based Systems Group (KBSG), RWTH-Aachen University)

Publications

2013

• Sandra Geisler, Christoph Quix

  Evaluation of Real-time Traffic Applications based on Data Stream Mining

  Published in Data Mining for Geoinformatics: Methods and Applications, to appear

2012

• Sandra Geisler, Christoph Quix, Stefan Schiffer, Matthias Jarke

  An Evaluation Framework for Traffic Information Systems Based on Data Streams

  Published in Transportation Research Part C, Special Issue on Data Management in Vehicular Networks, Volume 23, August 2012, pp. 29–55

2011

• Sandra Geisler, Sven Weber, Christoph Quix

  Ontology-based Data Quality Framework for Data Stream Applications

  Published in Proc. of the 16th International Conference on Information Quality, November 2011, Adelaide, AUS

2010

• Sandra Geisler, Christoph Quix, Stefan Schiffer

  A Data Stream-based Evaluation Framework for Traffic Information Systems

  Published in ACM SIGSPATIAL International Workshop on GeoStreaming (IWGS) 2010, November 2, 2010, San Jose, CA, USA

• Sandra Geisler, Yuan Chen, Christoph Quix, G. G. Gehlen

  Accuracy Assessment for Traffic Information Derived from Floating Phone Data

  Published in 17th Intelligent Transportation Systems and Services World Congress, Busan, South Korea, 2010.

2009

• Christoph Quix, Xiang Li, David Kensche, Sandra Geisler

  View Management Techniques and Their Application to Data Stream Management

  Published in P. Furtado (ed.): Evolving Application Domains of Data Warehousing and Mining - Trends and Solutions, Information Science Reference, pp. 83-112, 2009.

• Sandra Geisler, Christoph Quix, G. G. Gehlen, G. Jodlauk

  A quality- and priority-based traffic information fusion architecture

  Published in Proc. of the 16th ITS World Congress Stockholm 2009