TU Darmstadt / ULB / TUbiblio

Overcoming Challenges of Validation Automated Driving and Identification of Critical Scenarios

Wang, Cheng ; Winner, Hermann
IEEE (Corporate Creator) (2019):
Overcoming Challenges of Validation Automated Driving and Identification of Critical Scenarios.
pp. 2639-2644, Auckland, New Zealand, 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 27-30 October 2019, DOI: 10.1109/ITSC.2019.8917045,
[Conference or Workshop Item]

Abstract

Automated driving has arisen more and more attention both in traditional automobile industries and in IT companies. Rapid development and significant results have been achieved. However, there are few effective and satisfying methods to prove that Highly Automated Driving (HAD) is currently at least as safe as a human driver. In this paper, a novel validation method named Virtual Assessment of Automation in Field Operation (VAAFO) is introduced in detail. In VAAFO, HAD system has no access to actuators but runs in parallel while human driver drives the vehicle. Behavior comparison between human-driven vehicle and HAD in same scenario is a main new feature in VAAFO to validate automated driving and find out potential critical scenarios. Combined with correction of world model and criticality metrics, potential critical scenarios are filtered further to identify real critical scenarios. Different modules of VAAFO are explained elaborately based on these working principles. In principle, the proposed method could accelerate testing and validation of HAD a lot without bringing additional risks. Moreover, critical scenarios will be identified as well.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Wang, Cheng ; Winner, Hermann
Title: Overcoming Challenges of Validation Automated Driving and Identification of Critical Scenarios
Language: English
Abstract:

Automated driving has arisen more and more attention both in traditional automobile industries and in IT companies. Rapid development and significant results have been achieved. However, there are few effective and satisfying methods to prove that Highly Automated Driving (HAD) is currently at least as safe as a human driver. In this paper, a novel validation method named Virtual Assessment of Automation in Field Operation (VAAFO) is introduced in detail. In VAAFO, HAD system has no access to actuators but runs in parallel while human driver drives the vehicle. Behavior comparison between human-driven vehicle and HAD in same scenario is a main new feature in VAAFO to validate automated driving and find out potential critical scenarios. Combined with correction of world model and criticality metrics, potential critical scenarios are filtered further to identify real critical scenarios. Different modules of VAAFO are explained elaborately based on these working principles. In principle, the proposed method could accelerate testing and validation of HAD a lot without bringing additional risks. Moreover, critical scenarios will be identified as well.

Place of Publication: Auckland, New Zealand
Uncontrolled Keywords: Highly automated driving;Validation;Testing;Safety;Critical Scenarios;Measurement
Divisions: 16 Department of Mechanical Engineering
16 Department of Mechanical Engineering > Institute of Automotive Engineering (FZD)
16 Department of Mechanical Engineering > Institute of Automotive Engineering (FZD) > Driver Assistance
16 Department of Mechanical Engineering > Institute of Automotive Engineering (FZD) > Safety
Event Title: 2019 IEEE Intelligent Transportation Systems Conference (ITSC)
Event Dates: 27-30 October 2019
Date Deposited: 13 Oct 2020 05:31
DOI: 10.1109/ITSC.2019.8917045
Additional Information:

© 2019 IEEE. Personal use of this material is permitted.Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details