Hybrid Testing: A Vehicle-in-the-Loop Testing Method for the Development of Automated Driving Functions

Selim Solmaz*, Martin Rudigier, Marlies Mischinger, Jakob Reckenzaun

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The development of automated driving and Adaptive Driver-Assistance System (ADAS) functions requires extensive testing and validation prior to deployment. In general, exhaustive real-life scenario validation of such systems is not feasible and is overly time consuming. Moreover, simulation-only evaluations and testing are often deemed as inadequate due to the unmodeled dynamics and the lack of 1-1 correspondence with real-life testing. As a remedy, we describe in this article a novel test methodology called the "Hybrid Testing,"which was developed in the scope of the EU-H2020 project INFRAMIX, which enables the evaluation of a real vehicle in a virtual scenario in an enclosed proving ground with simulated traffic components and sensor signals, thereby combining the benefits of simulation and real-life testing. We show the utilization of this novel testing methodology for the evaluation of a trajectory planning (TP) algorithm to demonstrate its working principles and benefits.

Original languageEnglish
JournalSAE International Journal of Connected and Automated Vehicles
Volume4
Issue number1
DOIs
Publication statusPublished - 17 Mar 2021

Keywords

  • ADAS functions
  • Automated driving
  • Mixed reality
  • SUMO
  • Trajectory planner
  • Virtual testing

ASJC Scopus subject areas

  • Automotive Engineering
  • Computer Science Applications
  • Artificial Intelligence
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Hybrid Testing: A Vehicle-in-the-Loop Testing Method for the Development of Automated Driving Functions'. Together they form a unique fingerprint.

Cite this