The SOTIF standard (ISO 21448) requires scenario-based testing to verify and validate Advanced Driver Assistance Systems and Automated Driving Systems but does not suggest any practical way to do so effectively and efficiently. Existing scenario generation approaches either focus on exploring or exploiting the scenario space. This generally leads to test suites that cover many known cases but potentially miss edge cases or focused test suites that are effective but also contain less diverse scenarios. To generate SOTIF-compliant test suites that achieve higher coverage and find more faults, this paper proposes semi-concrete scenarios and combines them with parameter sampling to adequately balance scenario space exploration and exploitation. Semi-concrete scenarios enable combinatorial scenario generation techniques that systematically explore the scenario space, while parameter sampling allows for the exploitation of continuous parameters. Our experimental results show that the proposed concept can generate more effective test suites than state-of-the-art coverage-based sampling. Moreover, our results show that including a feedback mechanism to drive parameter sampling further increases test suites' effectiveness.

翻译：SOTIF标准（ISO 21448）要求采用基于场景的测试方法验证高级驾驶辅助系统和自动驾驶系统，但未提出任何兼具高效性与有效性的实践方案。现有场景生成方法要么侧重于探索场景空间，要么专注于利用场景空间，这通常会导致两类测试集：一类能覆盖大量已知情况但可能遗漏极端场景，另一类虽具有较高针对性却缺乏场景多样性。为生成符合SOTIF标准且兼具高覆盖率与高缺陷发现能力的测试集，本文提出半具体场景概念，并将其与参数采样相结合以平衡场景空间的探索与利用。半具体场景可实现组合式场景生成技术，通过系统性探索场景空间，而参数采样则能实现对连续参数的利用。实验结果表明，相较于现有基于覆盖率的采样方法，所提概念能生成更有效的测试集。此外，引入反馈机制驱动参数采样可进一步提升测试集有效性。