Advertisement

Is artificial intelligence the solution to all our problems? Exploring the applications of AI for automated driving

  • Stefan Milz
  • Jörg Schrepfer
Conference paper
Part of the Proceedings book series (PROCEE)

Zusammenfassung

Deep Learning and AI has become the standard model for object detection and recognition such as situation understanding, prediction and planning. In this chapter we explore how AI can be used to improve parts of the classical ADAS algorithm chain. Based on this, we investigate the full Automated Driving pipeline. Firstly, we describe the building blocks of the pipeline composed of standard computer vision tasks. We provide an overview of use cases for automated driving based on the authors’ experience in commercial deployment, e.g. Sensor-Fusion, Perception, SLAM or End-2-End Driving. Finally, we discuss the opportunities of using AI and Deep Learning to improve upon state-of-the-art classical methods.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. [1].
    Valeo: Automated driving challenges with Valeo Cruise4U. Online: https://www.youtube.com/watch?v=MJWrVyL1_n8, access: 27 October 2017
  2. [2].
    Navya: Navya launches autonom cab, the first 100-% autonomous robo taxi. Online: http://navya.tech/en/press/navya-launchs-autonom-cab-inparis/, access: 22 November 2017
  3. [3].
    Schaller, T.; Uhler, W.; Schrepfer, J.: Proposal for standardization of sensor interfaces to a fusion unit”; VDI conference Eliv 2017, Bonn, 18 and 19 October 2017Google Scholar
  4. [4].
    Jo, K.; Bradai, B.; Resende, P.; Picron, V.: Precise ego-localization using multi sensor map matching for highly and fully automated vehicles. SIA Cesa 2016 Congress, Paris, 16 and 17 November 2016Google Scholar
  5. [5].
    Spandfelder, B.: Challenges in applying the ISO 26262 for driver assistance systems. 5th Conference on Driving Assistance, Munich, 15 and 16 May 2012Google Scholar
  6. [6].
    ISO/TC 22/SC 32: N0356 Standardization of sensor interfaces. German proposal, ISO SC 32 sensing workshop, Berlin, 6 and 7 March 2017Google Scholar
  7. [7].
    Fitzek, F.; et al.: Cross-industry cooperation for camera technology standardization. VDI conference Eliv 2017, Bonn, 18 and 19 October 2017Google Scholar
  8. [8].
    Reilhac, P.; Moizard, J.; Kaiser, F.: Cockpit Concept for Conditional Automated Driving. In: ATZworldwide 118 (2016), No. 3, pp. 42-46CrossRefGoogle Scholar
  9. [9].
    DLR Cologne: Pegasus Research Project. Online: http://www.pegasusprojekt.info/en/home, access: 27 October 2017
  10. [10].
    Bradai, B.; Picron, V.; Heitzmann, T.; Maurel, P.; Randriazanamparany, R.; Taccoen, D.; Slimi, H.: Automated driving for all: entry mated. SIA Cesa 2016 Congress, Paris, 16 and 17 November 2016Google Scholar
  11. [11].
    Valeo: Valeo launches Valeo.AI, the first global research center in artificial intelligence and deep learning for automotive applications based in Paris. Online: http://www.valeo.com/en/valeo-launchesvaleo-ai-the-first-global-research-center-inartificial-intelligence-and-deep-learning-for-automotive-applications-based-in-paris/, access: 27 October 2017
  12. [12].
    Simon,S et al: Complex-YOLO: Real-time 3D Object Detection on Point CloudsGoogle Scholar
  13. [13].
    Bansal et al: ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the WorstGoogle Scholar
  14. [14].
    J. Schrepfer, J. Mathes, V. Picron, H. Barth: Automated driving and its sensors in test. ATZ Journal January 2018Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020

Authors and Affiliations

  • Stefan Milz
    • 1
  • Jörg Schrepfer
    • 1
  1. 1.Valeo Schalter und Sensoren GmbHKronachDeutschland

Personalised recommendations