Integrated 4D driver modelling under uncertainty (i4Driving)

不确定性下的集成 4D 驾驶员建模 (i4Driving)

• 批准号: 10038791
• 金额: $ 70.34万
• 依托单位: UNIVERSITY OF WARWICK
• 依托单位国家: 英国
• 项目类别: EU-Funded
• 财政年份: 2022
• 资助国家: 英国
• 起止时间: 2022 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=10038791
• 关键词: Integrated; 4D; driver; modelling; under

The vision of i4Driving is to lay the foundation for a new industry-standard methodology to establish a credible and realistic human road safety baseline for virtual assessment of CCAM systems. The two central ideas we propose are (1) a multi-level, modular and extendable simulation library that combines existing and new models for human driving behaviour; in combination with (2) an innovative cross-disciplinary methodology to account for the huge uncertainty in both human behaviours and use case circumstances. This rigorous treatment of the uncertainty is crucial to assess how much of our confidence in model inputs, parameters, and structure is justified. It also makes explicit how experts from different disciplines judge the outcomes and how justified the underlying assumptions really are. Our consortium combines all the expertise needed to develop this methodology (e.g., traffic engineering, human factors, data & computer science). We have the experimental means to gather the evidence beyond the state-of-art needed to realistically simulate (near) accidents in multi-driver scenarios (access to many data sources, advanced driving simulators, and field labs). We have a strong international network to collaborate with and harmonize our approach with academic and professional partners. Finally, we have all the relevant partners on-board to test and apply the methodology (Universities and research labs, OEMs and Tier 1, vehicle regulators, type-approval authorities, standardization institutes, insurance companies). i4Driving offers a proposition for the short and the longer term: a set of building blocks that pave the way for a driving license for AVs.

i4 Driving的愿景是为新的行业标准方法奠定基础，为CCAM系统的虚拟评估建立可信和现实的人类道路安全基线。我们提出的两个中心思想是：（1）一个多层次、模块化和可扩展的模拟库，它结合了人类驾驶行为的现有模型和新模型;（2）一种创新的跨学科方法，用于解释人类行为和用例环境中的巨大不确定性。这种对不确定性的严格处理对于评估我们对模型输入、参数和结构的信心有多大是合理的至关重要。它还明确了来自不同学科的专家如何判断结果，以及基本假设的合理性。我们的联盟结合了开发这种方法所需的所有专业知识（例如，交通工程、人为因素、数据和计算机科学）。我们有实验手段来收集证据，这些证据超出了在多驾驶员场景中逼真地模拟（接近）事故所需的最新技术水平（访问许多数据源，先进的驾驶模拟器和现场实验室）。我们有一个强大的国际网络，与学术和专业合作伙伴合作并协调我们的方法。最后，我们拥有所有相关合作伙伴来测试和应用该方法（大学和研究实验室、OEM和Tier 1、车辆监管机构、型式认证机构、标准化机构、保险公司）。i4 Driving提供了一个短期和长期的建议：一套为自动驾驶汽车驾驶执照铺平道路的构建模块。