Learning through AMBient Driving styles for Autonomous-Vehicles. LAMBDA-V

“我们的愿景是通过使用人类驾驶车辆的”真实的世界“行为数据来定义新的自动化车辆并制定规则，从而更快地实现高度自动化车辆（CAV）在安全性和容量方面的潜在优势。从现有车辆的数据中构建这些系统可能是可行的，而不仅仅是基于人类在特定情况下驾驶车辆的道路法规。这些可以通过模拟CAVS和其他车辆在混合车队中的行为来“调整”。这将有助于定制早期CAV行为以匹配人类驾驶员，提高早期采用者的信心。我们希望了解处理现有海量数据集的可行性，了解建模人类驾驶员所需的参数以及如何扩展它们以制定车辆规则，改进当前技术并建模影响以平衡舒适性，容量和安全性。这可以确保CAV行为符合监管机构和客户的需求。我们专注于在混合车队环境中创新地探索完整的端到端数据链和商业模式。这整合了车辆制造商和道路运营商对CAV行为的看法，并研究了如何为其他CAV项目开发符合隐私法的数据集。它汇集了那些开发CAV和建模软件的人，他们的数据来自英国各地大量匿名驾驶员的混合车队，而不是一个地点的小型专业车辆车队。由CloudMade领导，带来了机器学习和人类驾驶员行为建模的专业知识，合作伙伴包括伯明翰市理事会，作为一个拥有法律的权力和职责的高速公路管理局，来自道路运营和Trakm8的TSS和AA，他们将提供来自数千辆AA成员车辆的匿名样本数据，这些车辆配备了创新的Car Genie设备。我们的主要成果将是为所有合作伙伴确定潜在的产品改进，使数据、建模和规则产生新的销售。如果这个想法可行，好处将是减少对交通的不可预见的影响，CAVS规则的专利，更好地理解人类和自动驾驶车辆的早期混合车队运营，以及如何使早期的自动驾驶车辆对用户有吸引力。它将帮助公路当局和车辆制造商了解如何在各种真实的世界道路上部署CAVs。这是一项为期一年的可行性研究，提供在全球范围内利用这一想法所需的技术创新和业务变革。"

"Our vision is for the potential benefits in safety and capacity of highly automated vehicles (CAVs) to be achieved more quickly, by using data on 'real world' behaviour of human driven vehicles to define and rules for new automated ones that improve on human safety and driving capability. It may be feasible to build these from data from existing vehicles, based not just on road laws how humans drive vehicles in specific circumstances. These could be 'tuned' by modelling how CAVS and other vehicles then behave in a mixed fleet. This will help tailor early CAV behaviour to match that of human drivers, improving confidence for early adopters.We want to understand the feasibility of processing existing massive datasets, to understand the parameters needed for modelling human drivers and how to extend them to make vehicle rules, improving current technology and modelling impact to balance comfort, capacity and safety. This could ensure CAV behaviour meets needs of regulators and customers.We focus on innovatively exploring a full end to end data chain and business model in a mixed fleet environment. This integrates vehicle maker and road operator perspectives on CAV behaviour and examines how to develop privacy law compliant datasets for other CAV projects. It brings together those who develop CAV and modelling software with data from massive mixed fleets of anonymised drivers across the UK, rather than small fleets of specialised vehicles in one location.Led by CloudMade, bringing expertise in machine learning and human driver behaviour modelling, the partners include Birmingham City Council as a highway authority with legal powers and duties, TSS from road operations and Trakm8 and the AA who will provide anonymised sample data from many thousands of AA member's vehicles equipped with the innovative Car Genie device. Our key output will be identifying potential product improvements for all partners to make data, modelling and rules generate new sales.The benefits if the idea is feasible would be reduced unforeseen impacts on traffic, patents on rules for CAVS, an improved understanding of early mixed fleet operation of human and automated vehicles and how to make early level self driving vehicles attractive to users. It will help highways authoritiesand vehicle makers alike understand how to deploy CAVs on a variety of real world roads.It is a 1-year feasibility study delivering technology innovation and business change needed for exploiting the idea globally."