自动驾驶系统动态驾驶任务评估（DA）指标

[中文适用范围]： 本SAE推荐实践提供了用于量化自动驾驶系统（ADS）操作车辆的驾驶员辅助系统（DA）性能的DA指标。此处的重点是与安全相关的DA性能，包括每个指标的定义、分类、特性及其使用（包括替代方案）。DA性能是ADS操作车辆整体操作性能的一个子集。因此，虽然对DA回退[1]、网络安全、维护、与乘客的互动等的评估可能具有重要性，并可能间接影响DA性能，但这些内容超出了本文档的范围。请注意，DA指标并未规定（由ADS操作的）被测车辆（SV）应执行的操作和/或动作。尽管本文档提供了一组独立的DA指标，但需要注意的是，本文档的范围不包括描述这些指标在实践中应如何应用。这是因为DA指标的实施必须考虑具体场景或部署的整体背景，而不同DA指标可能适用于不同的ADS应用。本文档中推荐的DA指标的实施可以为评估ADS的DA性能提供安全评估信息，而这一评估反过来可以为ADS操作车辆的更广泛的安全评估提供依据。然而，这些指标可能需要补充其他输入，以用于这两种类型的评估。本文档对之前研究中提出并部分应用的DA指标进行了文献综述，并根据该综述创建了一组带有示例使用情况的DA指标。在适当的情况下，还包含了显示某个指标与安全结果之间存在有意义关系的先前研究证据。该组DA指标不一定全面，可能还有其他可用于评估DA性能的指标，尤其是那些衡量ADS子系统性能的指标。DA指标在其定义中可能会使用参数化变量、假设和阈值。为这些指标定义或推荐这些变量的值不在本文档的范围内。预计用于收集和分配这些指标值的方法将基于本文档中所提出指标在实际应用中的实施，以及生产车辆和原型系统在实际使用中的经验。这些值还可能由法规、行业最佳实践、技术进步和学术研究等建立，并可能根据操作设计域（ODD）内的运行条件而变化。在此期间，使用这些指标的实施者将负责选择这些变量的值。DA指标可以在测试阶段和商业化阶段实施，并可用于各种目的，包括配备ADS的车辆开发、第三方评估以及事件重建和分析。例如，这些指标可以作为配备ADS车辆验证与确认（V&V）基于场景测试过程的一部分，其中对各个场景进行测试。第三方评估者也可以在实际道路运行（可能是在测试或商业化期间）中，对一段时间内或一定数量的场景（即一段时间可被视为一系列场景）的指标测量值进行汇总，以监控ADS操作车辆的驾驶性能。 [外文原描述]： This SAE Recommended Practice provides DA metrics used to quantify the DDT performance of ADS-operated vehicles.2x Here, the primary focus is on the safety-related DDT performance and includes definitions, taxonomy, characteristics, and usage (along with alternatives) for each metric. DDT performance is a subset of overall operational performance of ADS-operated vehicles. Thus, assessments of DDT Fallback [1], cybersecurity, maintenance, interactions with passengers, etc., while important and could have an indirect impact on the DDT, are out of scope for this document. Note that the DA metrics do not specify the actions and/or maneuvers to be executed by the (ADS-operated) subject vehicle (SV). While this document presents a set of individual DA metrics, it is important to note that it is out of the scope of this document to describe how these metrics should be applied in practice. This is because the overall context of the scenario or deployment must be considered during DA metrics implementation and different DA metrics could be applicable for different ADS applications. Implementation of the DA metrics recommended in this document may inform a safety assessment of an ADS’s performance of the DDT, and this assessment in turn may inform a broader safety assessment of an ADS-operated vehicle. However, these metrics could be supplemented by additional input for both types of assessments. A literature review of DA metrics that have been proposed and, in some cases, used in previous studies was conducted. From this literature review, a set of DA metrics has been created with example usage. Evidence of prior research indicating that a metric has a meaningful relationship with safety outcome(s) is included where applicable.2x The set of DA metrics is not necessarily comprehensive, and there may be additional metrics that can be used to assess DDT performance, particularly metrics that measure ADS subsystem performance.2x DA metrics might use parameterized variables, assumptions, and thresholds2x in their formulation. Defining or recommending values for these quantities used in the metrics formulation is outside the scope of this document. It is expected that the methodologies for collecting and assigning such values for these metrics will be developed based on implementation of the metrics in this document in field and other learned experiences with production and prototype vehicles and systems. Values could also be established by regulation, industry best practices, improved technology development, and academic research, among others, and may change based on the operating conditions within the operational design domain (ODD). In the interim, it will be the responsibility of the implementer of these metrics to choose values for these quantities. The DA metrics can be implemented in both testing and commercialization phases and for various purposes, including for ADS-equipped vehicle development, third-party evaluation, and event reconstruction and analysis. For example, the metrics can be used as part of an ADS-equipped vehicle verification and validation (V&V) scenario-based testing process wherein individual scenarios are tested. A third-party evaluator could also aggregate measurements of the metrics measurements over a period of time or number of scenarios (i.e., a period of time could be considered to be a sequence of scenarios) in on-road operation (which could be during testing or commercialization) in order to monitor driving performance of an ADS-operated vehicle.