A Novel Approach to Integrate Human-in-the-Loop Testing in the Development Chain of Automated Driving: The Example of Automated Lane Change

Abstract

Abstract For market introduction of advanced driver assistant (ADAS) and automated driving (AD) systems on full vehicle level, testing and validation is one of the biggest challenges. The present study describes a novel approach that integrates a driving simulator in a virtual development process aiming to reduce time and effort for system development. The approach is demonstrated on a specific automated lane change assist (LCA) system. To this end, the LCA function and the corresponding human machine interface (HMI) are developed and implemented in the driving simulator. The core of the approach is a driving simulator-based testing method which proposes a novel two stage testing concept and involves multiple test drivers. The method provides better insight into the overall system performance and, moreover, detects potentials for improvements dedicated for the ADAS functionalities as well as for the design of the HMI system. Using this method, a driving simulator study with 20 volunteer drivers is conducted to evaluate the LCA system with respect to driver acceptance and user friendliness. The results of the study will be used for the parametrization and fine tuning of the LCA function as well as for the HMI improvement.