Jump to ContentJump to Main Navigation
Show Summary Details
More options …

at - Automatisierungstechnik

Methoden und Anwendungen der Steuerungs-, Regelungs- und Informationstechnik

[AT - Automation Technology: Methods and Applications of Control, Regulation, and Information Technology
]

Editor-in-Chief: Jumar, Ulrich


IMPACT FACTOR 2018: 0.500

CiteScore 2018: 0.60

SCImago Journal Rank (SJR) 2018: 0.211
Source Normalized Impact per Paper (SNIP) 2018: 0.532

Online
ISSN
2196-677X
See all formats and pricing
More options …
Volume 66, Issue 2

Issues

Risk estimation for driving support and behavior planning in intelligent vehicles

Risikoprädiktion für die Fahrerunterstützung und Verhaltensplanung in intelligenten Fahrzeugen

Julian Eggert
Published Online: 2018-02-10 | DOI: https://doi.org/10.1515/auto-2017-0132

Abstract

Vehicles will be equipped with sensors and functions for highly automated driving in the foreseeable future. A big topic of research on the way to this goal is how to convey to these vehicles an understanding of the driving situations that is comparable to that of humans. For safe driving, this requires predicting how a scene will evolve and anticipating how dangerous it will potentially be. Risk estimation is a central ingredient in this process. In this paper, we describe how risk modeling frameworks help in managing the complexity of the driving task. We approach risk from the perspective of rare probabilistic events in environments where predictions might be inherently uncertain, and explain how this leads to a survival-based formulation which allows to model different types of risks encountered in driving situations within a single unified concept. In addition, we show how the framework can be used for driving behavior evaluation and risk-avoiding trajectory planning.

Zusammenfassung

In naher Zukunft werden Fahrzeuge mit einer Vielzahl von Sensoren und Systemen für das hochautomatisierte Fahren ausgerüstet sein. Eine wichtige Forschungsfrage ist, wie diese Systeme ein Verständnis der Fahrsituationen erlangen können, welches mit dem von Menschen vergleichbar ist. Sicheres automatisiertes Fahren erfordert dafür eine verlässliche Risikoabschätzung, wobei prädiziert werden muss, wie sich eine Verkehrsszene entwickeln wird, und was das für das eigene Verhalten bedeutet. In diesem Artikel skizzieren wir Modelle und Systeme für eine Risikoabschätzung, die auf einem Ansatz von spärlichen probabilistischen Ereignissen und der Berechnung einer sogenannten „Überlebenswahrscheinlichkeit“ basieren. Der Ansatz eignet sich für eine einheitliche Erfassung von verschiedenen Arten von Risiken, und ermöglicht Anwendungen in der risikovermeidenden Fahrerunterstützung und der Trajektorienplanung bei intelligenten Fahrzeugen.

Keywords: Risk Modelling; Risk Maps; Foresighted/Predictive Driving; Highly Automated Driving; Survival Probability; Behavior and Trajectory Planning

Schlagwörter: Risikomodellierung; Risikokarten; Vorausschauendes Fahren; Hochautomatisiertes Fahren; Überlebenswahrscheinlichkeit; Verhaltens- und Trajektorienplanung

References

  • 1.

    BMVI. Maßnahmenplan der Bundesregierung zum Bericht der Ethik-Kommission Automatisiertes und Vernetztes Fahren. Technical report, Die Bundesregierung, 2017. www.bmvi.de/SharedDocs/DE/Publikationen/DG/massnahmenplan-zum-bericht-der-ethikkommission-avf.pdf?__blob=publicationFile.Google Scholar

  • 2.

    Ashwin Carvalho, Stéphanie Lefévre, Georg Schildbach, Jason Kong, and Francesco Borrelli. Automated driving: The role of forecasts and uncertainty – a control perspective. European Journal of Control, 24(Supplement C):14–32, 2015.CrossrefWeb of ScienceGoogle Scholar

  • 3.

    On-Road Automated Driving (Orad) Committee. Taxonomy and definitions for terms related to on-road motor vehicle automated driving systems. Technical report, Society of Automotive Engineers (SAE), 2014. standards.sae.org/j3016_201401/.Google Scholar

  • 4.

    Florian Damerow and Julian Eggert. Spatio-temporal trajectory similarity and its application to situation classification and the evaluation of lack of interaction. In International Conference on Intelligent Transportation Systems (ITSC), pages 2512–2519. IEEE, 2016.Google Scholar

  • 5.

    Florian Damerow and Julian Eggert. Predictive risk maps. In International Conference on Intelligent Transportation Systems (ITSC), pages 703–710. IEEE, 2014.Google Scholar

  • 6.

    Florian Damerow and Julian Eggert. Balancing risk against utility: Behavior planning using predictive risk maps. In Intelligent Vehicles Symposium (IV), pages 857–864. IEEE, 2015.Google Scholar

  • 7.

    Florian Damerow, Tim Puphal, and Julian Eggert. Risk-based driver assistance for approaching intersections of limited visibility. In International Conference on Vehicular Electronics and Safety (ICVES), pages 178–184. IEEE, 2017.Google Scholar

  • 8.

    International Traffic Safety Data and Paris Analysis Group. Road safety annual report 2015. Technical report, OECD/ITF (International Transport Forum), 2015. Retrieved 2016-01-29, data from 2013.

  • 9.

    Thao Dang, Gabi Breuel, Andreas Tamke, Andreas Wedel, Wolfgang Rosenstiel, Dietmar Kasper, and Galia Weidl. Object-oriented bayesian networks for detection of lane change maneuvers. IEEE Intelligent Transportation Systems Magazine, 4(3):19–31, 2012.Web of ScienceCrossrefGoogle Scholar

  • 10.

    Julian Eggert. Predictive risk estimation for intelligent ADAS functions. In International Conference on Intelligent Transportation Systems (ITSC), pages 711–718. IEEE, 2014.Google Scholar

  • 11.

    Julian Eggert. Solomon curve 2020: Relating microscopic risk models with accident statistics. In International Conference on Intelligent Transportation Systems (ITSC), pages 2293–2300. IEEE, 2016.Google Scholar

  • 12.

    Julian Eggert, Florian Damerow, and Stefan Klingelschmitt. The foresighted driver model. 2015 IEEE Intelligent Vehicles Symposium (IV), pages 322–329, 2015.Google Scholar

  • 13.

    Julian Eggert, Stefan Klingelschmitt, and Florian Damerow. The foresighted driver: Future ADAS based on generalized predictive risk estimation. In FAST-zero Symposium, Gothenburg, Sweden, 2015.Google Scholar

  • 14.

    Julian Eggert and Tim Puphal. Continuous risk measures for adas and ad. In FAST-zero Symposium, Nara, Japan, 2017.Google Scholar

  • 15.

    Ethik-Kommission. Automatisiertes und Vernetztes Fahren. Technical report, Bundesministerium für Verkehr und digitale Infrastruktur, 2017. www.bmvi.de/bericht-ethikkommision.Google Scholar

  • 16.

    D. González, J. Pérez, V. Milanés, and F. Nashashibi. A review of motion planning techniques for automated vehicles. IEEE Transactions on Intelligent Transportation Systems, 17(4):1135–1145, April 2016.CrossrefWeb of ScienceGoogle Scholar

  • 17.

    ISO31000. Risk management – principles and guidelines. International Organization for Standardization, Geneva, Switzerland, 2009.

  • 18.

    Kristian Kroschel, Jörg Hillenbrand, and Andreas M. Spieker. A multilevel collision mitigation approach – its situation assessment, decision making, and performance tradeoffs. IEEE Transactions on Intelligent Transportation Systems, 7(4):528–540, 2006.CrossrefGoogle Scholar

  • 19.

    Sertac Karaman and Emilio Frazzoli. Optimal kinodynamic motion planning using incremental sampling-based methods. In Proceedings of the 49th IEEE Conference on Decision and Control, CDC 2010, Atlanta, Georgia, USA, December 15–17, 2010, pages 7681–7687, 2010.Google Scholar

  • 20.

    Sertac Karaman, Matthew R. Walter, Alejandro Perez, Emilio Frazzoli, and Seth J. Teller. Anytime motion planning using the RRT. In IEEE International Conference on Robotics and Automation, ICRA 2011, Shanghai, China, 9–13 May 2011, pages 1478–1483, 2011.Google Scholar

  • 21.

    Marcus Kleinehagenbrock, Morimichi Nishigaki, Robert Kastner, Jens Schmüdderich, Sven Rebhan, Thomas Weisswange, Hiroyuki Kamiya, Shunsuke Kusuhara, Naoki Mori, and Shinnosuke Ishida. Introduction of Intelligent Adaptive Cruise Control (i-ACC) – a predictive safety system. In FAST-zero Symposium, Gothenburg, Sweden, 2015.Google Scholar

  • 22.

    Stefan Klingelschmitt, Florian Damerow, and Julian Eggert. Managing the complexity of inner-city scenes: An efficient situation hypotheses selection scheme. In Intelligent Vehicles Symposium (IV), pages 1232–1239, 2015.Google Scholar

  • 23.

    Stefan Klingelschmitt, Florian Damerow, Volker Willert, and Julian Eggert. Probabilistic situation assessment framework for multiple, interacting traffic participants in generic traffic scenes. In Intelligent Vehicles Symposium (IV), pages 1141–1148, 2016.Google Scholar

  • 24.

    Stefan Klingelschmitt, Volker Willert, and Julian Eggert. Probabilistic, discriminative maneuver estimation in generic traffic scenes using pairwise probability coupling. In International Conference on Intelligent Transportation Systems (ITSC), pages 1269–1276. IEEE, 2016.Google Scholar

  • 25.

    Steven M. Lavalle. Rapidly-exploring random trees: A new tool for path planning. Technical report, Computer Science Dept., Iowa State University, 1998.

  • 26.

    Stéphanie Lefèvre, Dizan Vasquez, and Christian Laugier. A survey on motion prediction and risk assessment for intelligent vehicles. ROBOMECH Journal, 1(1):1, 2014.CrossrefGoogle Scholar

  • 27.

    Michiel M. Minderhoud and Piet H. L. Bovy. Extended time-to-collision measures for road traffic safety assessment. In Accid. Anal. Prev., volume 33, pages 89–97, 2014.Google Scholar

  • 28.

    US Department of Transportation. National motor vehicle crash causation survey. Technical report, NHTSA, 2008. crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/811059.Google Scholar

  • 29.

    US Department of Transportation. Critical reasons for crashes investigated in the national motor vehicle crash causation survey. Technical report, NHTSA, 2015. crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/812115.Google Scholar

  • 30.

    US Department of Transportation. Automated driving systems (ADS): A vision for safety 2.0. Technical report, NHTSA, 2017. www.nhtsa.gov/sites/nhtsa.dot.gov/files/documents/13069a-ads2.0_090617_v9a_tag.pdf.Google Scholar

  • 31.

    Brian Paden, Michal Cap, Sze Zheng Yong, Dmitry Yershov, and Emilio Frazzoli. A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles. Intelligent Vehicles Journal, 1:33–55, 2016.CrossrefGoogle Scholar

  • 32.

    Jens Schmüdderich, Sven Rebhan, Thomas Weisswange, Marcus Kleinehagenbrock, Robert Kastner, Morimichi Nishigaki, Shunsuke Kusuhara, Hiroyuki Kamiya, Naoki Mori, and Shinnosuke Ishida. A novel approach to driver behavior prediction using scene context and physical evidence for intelligent Adaptive Cruise Control (i-ACC). In FAST-zero Symposium, Gothenburg, Sweden, 2015.Google Scholar

  • 33.

    Matthias Schreier, Volker Willert, and Jürgen Adamy. Bayesian, maneuver-based, long-term trajectory prediction and criticality assessment for driver assistance systems. In International Conference on Intelligent Transportation Systems (ITSC), pages 703–710. IEEE, 2014.Google Scholar

  • 34.

    Matthias Schreier, Volker Willert, and Jürgen Adamy. An integrated approach to maneuver-based trajectory prediction and criticality assessment in arbitrary road environments. IEEE Transactions on Intelligent Transportation Systems, 17:2751–2766, 2016.CrossrefWeb of ScienceGoogle Scholar

  • 35.

    Martin Treiber, Ansgar Hennecke, and Dirk Helbing. Congested traffic states in empirical observations and microscopic simulations. Phys. Rev. E, 62:1805–1824, 2000.CrossrefGoogle Scholar

  • 36.

    A. van der Horst. Time-to-Collision as a cue for decision making in braking, In Vision in Vehicles III, pages 19–26. Elsevier, 1991.Google Scholar

  • 37.

    Walther Wachenfeld, Philipp Junietz, Raphael Wenzel, and Hermann Winner. The Worst-Time-To-Collision Metric for Situation Identification. In Intelligent Vehicles Symposium (IV), 2016.Google Scholar

  • 38.

    James Ward, Gabriel Agamennoni, Stewart Worrall, and Eduardo Nebot. Vehicle Collision Probability Calculation for General Traffic Scenarios Under Uncertainty. In Intelligent Vehicles Symposium (IV), pages 986–992, 2014.Google Scholar

  • 39.

    Waymo. Waymo safety report: On the road to fully self-driving. Technical report, Waymo, 2017. storage.googleapis.com/sdc-prod/v1/safety-report/waymo-safety-report-2017.pdf.Google Scholar

  • 40.

    Wikipedia. Risk – Wikipedia, the free encyclopedia, 2014.

About the article

Julian Eggert

Dr. rer. nat. Julian Eggert is Chief Scientist at the Honda Research Institute Europe. His main research is on environment perception, situation analysis and knowledge-based prediction and reasoning for artificial cognitive systems.


Received: 2017-12-07

Accepted: 2018-01-18

Published Online: 2018-02-10

Published in Print: 2018-02-23


Citation Information: at - Automatisierungstechnik, Volume 66, Issue 2, Pages 119–131, ISSN (Online) 2196-677X, ISSN (Print) 0178-2312, DOI: https://doi.org/10.1515/auto-2017-0132.

Export Citation

© 2018 Walter de Gruyter GmbH, Berlin/Boston.Get Permission

Citing Articles

Here you can find all Crossref-listed publications in which this article is cited. If you would like to receive automatic email messages as soon as this article is cited in other publications, simply activate the “Citation Alert” on the top of this page.

[1]
Tim Puphal, Malte Probst, and Julian Eggert
IEEE Transactions on Intelligent Vehicles, 2019, Volume 4, Number 3, Page 406

Comments (0)

Please log in or register to comment.
Log in