Automated driving functions (ADFs) have become increasingly popular in recent years. However, their safety must be assured. Thus, the verification and validation of these functions is still an important open issue in research and development. To achieve this efficiently, scenario-based testing has been established as a valuable methodology among researchers, industry, as well as authorities. Simulations are a powerful way to test those scenarios reproducibly. In this paper, we propose a method to automatically test a set of scenarios in many variations. In contrast to related approaches, those variations are not applied to traffic participants around the ADF, but to the road network to show that parameters regarding the road topology also influence the performance of such an ADF. We present a continuous tool chain to set up scenarios, variate them, run simulations and finally, evaluate the performance with a set of key performance indicators (KPIs).

翻译：近年来，自动驾驶功能（ADFs）日益普及，但其安全性仍需得到保障。因此，对这些功能的验证与确认仍是研究与开发中亟待解决的重要问题。为实现高效验证，基于场景的测试方法已被研究人员、工业界及监管机构确立为一项重要方法论。仿真测试是场景可复现性验证的有力手段。本文提出一种方法，可自动对一组场景进行多变异测试。与现有方法不同，这些变异并非针对自动功能周围的交通参与者，而是应用于道路网络，以表明道路拓扑参数同样影响此类自动功能的性能。我们构建了一套连续工具链，用于场景搭建、变异生成、仿真运行，最终通过一组关键性能指标（KPIs）评估性能表现。