Title
Validating SuperHuman Automated Driving Performance
Author
Ajanovic, Zlatan (Virtual Vehicle Research GmbH)
Klomp, Matthijs (Volvo)
Lacevic, Bakir (University of Sarajevo)
Shyrokau, B. (TU Delft Intelligent Vehicles)
Pretto, Paolo (Virtual Vehicle Research GmbH)
Islam, Hassaan (Virtual Vehicle Research GmbH)
Stettinger, Georg (Virtual Vehicle Research GmbH)
Horn, Martin (Graz University of Technology)
Date
2020
Abstract
Closed-loop validation of autonomous vehicles is an open problem, significantly influencing development and adoption of this technology. The main contribution of this paper is a novel approach to reproducible, scenario-based validation that decouples the problem into several sub-problems, while avoiding to brake the crucial couplings. First, a realistic scenario is generated from the real urban traffic. Second, human participants, drive in a virtual scenario (in a driving simulator), based on the real traffic. Third, human and automated driving trajectories are reproduced and compared in the real vehicle on an empty track without traffic. Thus, benefits of automation with respect to safety, efficiency and comfort can be clearly benchmarked in a reproducible manner. Presented approach is used to benchmark performance of SBOMP planner in one scenario and validate SuperHuman driving performance.
Subject
automated driving
lane change
multi-lane driving
planning
SuperHuman
traffic lights
urban driving
validation
To reference this document use:
http://resolver.tudelft.nl/uuid:ac6f2d20-b84d-477f-9cdd-899be92649b8
DOI
https://doi.org/10.1109/SMC42975.2020.9282822
Publisher
IEEE, Piscataway, NJ, USA
Embargo date
2021-06-14
ISBN
978-1-7281-8526-2
Source
Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Event
2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020, 2020-10-11 → 2020-10-14, Toronto, Canada
Series
Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, 1062-922X, 2020-October
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
conference paper
Rights
© 2020 Zlatan Ajanovic, Matthijs Klomp, Bakir Lacevic, B. Shyrokau, Paolo Pretto, Hassaan Islam, Georg Stettinger, Martin Horn