TU Darmstadt / ULB / TUbiblio

Defining Required and Feasible Test Coverage for Scenario-Based Validation of Highly Automated Vehicles

Amersbach, Christian and Winner, Hermann (2019):
Defining Required and Feasible Test Coverage for Scenario-Based Validation of Highly Automated Vehicles.
In: 22nd IEEE Intelligent Transportation Systems Conference (ITSC) 2019, Auckland, New Zealand, 27-30 October 2019, [Online-Edition: https://tuprints.ulb.tu-darmstadt.de/8633],
[Conference or Workshop Item]

Abstract

A statistical, distance-based validation of highly automated vehicles is not feasible due to the high required testing distance. Scenario-based validation approaches promise to solve this issue. However, due to the high number of influence parameters, the number of possible parameter combinations is exploding. Therefore, exhaustive testing of all possible combinations is not feasible as well. Thus, a coverage criterion for scenario-based validation is required. Hereby, it is crucial that all stakeholders accept the coverage criterion. This paper proposes an approach to determine the number of scenarios that correspond to the required testing distance of the known distance-based approach. Furthermore, the number of scenarios that can be feasibly simulated for validation is estimated under certain assumptions. Comparing the required and the feasible number of scenarios shows that there is still a gap of around one order of magnitude. Nevertheless, combining this approach with other methods that aim to reduce the approval effort has the potential to get the required test coverage to a feasible level and therefore contribute to solving the validation challenge. However, there are still many remaining challenges, such as the availability of representative scenario catalogs or sufficient simulation models for environment perception sensors.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Amersbach, Christian and Winner, Hermann
Title: Defining Required and Feasible Test Coverage for Scenario-Based Validation of Highly Automated Vehicles
Language: English
Abstract:

A statistical, distance-based validation of highly automated vehicles is not feasible due to the high required testing distance. Scenario-based validation approaches promise to solve this issue. However, due to the high number of influence parameters, the number of possible parameter combinations is exploding. Therefore, exhaustive testing of all possible combinations is not feasible as well. Thus, a coverage criterion for scenario-based validation is required. Hereby, it is crucial that all stakeholders accept the coverage criterion. This paper proposes an approach to determine the number of scenarios that correspond to the required testing distance of the known distance-based approach. Furthermore, the number of scenarios that can be feasibly simulated for validation is estimated under certain assumptions. Comparing the required and the feasible number of scenarios shows that there is still a gap of around one order of magnitude. Nevertheless, combining this approach with other methods that aim to reduce the approval effort has the potential to get the required test coverage to a feasible level and therefore contribute to solving the validation challenge. However, there are still many remaining challenges, such as the availability of representative scenario catalogs or sufficient simulation models for environment perception sensors.

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
16 Department of Mechanical Engineering > Institute of Automotive Engineering (FZD) > Test Methods
Event Title: 22nd IEEE Intelligent Transportation Systems Conference (ITSC) 2019
Event Location: Auckland, New Zealand
Event Dates: 27-30 October 2019
Date Deposited: 19 May 2019 19:55
Official URL: https://tuprints.ulb.tu-darmstadt.de/8633
URN: urn:nbn:de:tuda-tuprints-86330
Additional Information:

Author-submitted article. © 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:

Optionen (nur für Redakteure)

View Item View Item