A Method for Classifying Test Bench Configurations in a Scenario-Based Test Approach for Automated Vehicles

05/22/2019
by   Markus Steimle, et al.
0

The introduction of automated vehicles demands a way to prove their safe operation. However, validating the safety of automated vehicles is still an unsolved problem. While the scenario-based test approach seems to provide a possible solution, it requires the execution of a high amount of test cases. Several test benches, from actual test vehicles to partly or fully simulated environments, are available, but choosing the optimal test bench, e.g. in terms of required execution time and costs, is a difficult task. Every test bench provides different elements, e.g. simulation models which can be used for test case execution. The composition of elements at a specific test bench is called test bench configuration. This test bench configuration determines the actual performance of a test bench and, therefore, whether the run of a particular test case provides valid test case results with respect to the intended purpose, e.g. a safety validation. For an effective and efficient test case execution, a method is required to assign test cases to the most appropriate test bench configuration. Therefore, it is indispensable to have a method to classify test bench configurations in a clear and reproducible manner. In this paper, we propose a method for classifying test benches and test bench configurations and illustrate the classification method with some examples. The classification method serves as a basis for a systematic assignment of test cases to test bench configurations which allows for an effective and efficient test case execution.

READ FULL TEXT

page 1

page 3

page 5

research
09/06/2021

ViSTA: a Framework for Virtual Scenario-based Testing of Autonomous Vehicles

In this paper, we present ViSTA, a framework for Virtual Scenario-based ...
research
03/17/2020

Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World

We present a new approach to automated scenario-based testing of the saf...
research
10/06/2021

Probabilistic Metamodels for an Efficient Characterization of Complex Driving Scenarios

To systematically validate the safe behavior of automated vehicles (AV),...
research
10/01/2017

A Versatile Approach to Evaluating and Testing Automated Vehicles based on Kernel Methods

Evaluation and validation of complicated control systems are crucial to ...
research
09/21/2022

PTSG: a test generation tool based on extended finite state machine

The Extended Finite State Machine (EFSM) is one of the most popular mode...

Please sign up or login with your details

Forgot password? Click here to reset