SCC-IRG Track 2: Data-Informed Modeling and Correct-by-Design Control Protocols for Personal Mobility in Intelligent Urban Transportation Systems

该智能互联社区项目将开发一个统一的基于模型和数据驱动的框架，用于建模和控制智能城市交通中个人移动性的三个核心组成部分：停车，乘车共享服务和城市主干道上的交通流量。 来自最近安装的技术的数据，如智能停车计时器和基于探头的传感器（例如，WiFi传感器）可以在，例如，设计动态停车定价，并使用智能设备应用程序帮助引导司机找到可用的停车位。这些数据将通过与洛杉矶和西雅图的交通部（DOT）的合作提供。此外，我们将与洛杉矶和西雅图的几个商业区合作，这些商业区是新停车系统的重要利益相关者，为非常多样化的社区提供服务。该项目将新技术与方法创新相结合，旨在减少交通拥堵对环境、生活质量、生产力以及身体和财务福祉的负面影响。 现场实验性试验将有助于评估研究建议的政策变化的影响。与市政合作伙伴的合作也将被用来创造劳动力发展的机会，使学生能够获得领域专家和研究能力建设的援助。 为了利用新的数据驱动技术，该项目将开发城市环境中停车、拼车和交通流的随机决策模型。该小组将探讨：i）基于随机博弈论（SG）和马尔可夫决策过程（MDP）的模型，以捕获车辆行为以及作为整体行为的交通动态; ii）使用形式化方法和凸优化合成正确的设计决策算法; iii）在相关城市环境中集成和测试所提出的算法。开发的模型将捕捉个人的行为以及整体城市交通动态，并将根据真实的数据进行验证。该项目将探索新的方法，将正式的方法与基于优化的MDP和SG合成决策政策，在个人和合奏水平，包括独特的一套规范。形式方法技术允许定性规范（例如，机会、公平性等）这些目标的目的是，拟议的设计正确的创新将导致确保可持续政策发展所需的可证明的保证。最后，与西雅图交通部的合作者一起，将在选定的西雅图商业区进行超越数据收集的实验性试验，以测试和验证设计的控制和停车政策的变化。

This Smart and Connected Communities project will develop a unified model-based and data-driven framework for modeling and controlling three core components of personal mobility in intelligent urban transportation: parking, ride-sharing services, and traffic flow on urban arterial roads. Data from recently installed technologies such as smart parking meters and probe-based sensors (e.g., wifi sensors) can be leveraged in, e.g., designing dynamic parking pricing and to help guide drivers to available parking spaces using smart-device apps. Such data will be available via collaborations with the Departments of Transportation (DOT) in Los Angeles and Seattle. Furthermore, we will engage several commercial districts in Los Angeles and Seattle, which are significant stakeholders in new parking systems and serve very diverse communities. Coupling new technologies with methodological innovations, this project aims to reduce negative impacts of traffic congestion on the environment, quality of life, productivity, and physical and financial well-being. In-situ experimental trials will allow for the impact of policy changes suggested by the research to be assessed. Collaborations with municipal partners will also be leveraged to create opportunities for workforce development that avail students to domain experts and aid in research-capacity building. In pursuit of utilizing new data-driven technologies, this project will develop stochastic decision models for parking, ride-sharing, and traffic flow in urban environments. The team will explore: i) Stochastic Game-theoretic(SG) and Markov Decision Process (MDP)-based models to capture vehicle behavior as well as the traffic dynamics as an ensemble behavior; ii) Synthesis of correct-by-design decision algorithms using formal methods and convex optimization; iii) Integration and testing of the proposed algorithms in a relevant urban environment. Developed models will capture individuals' behaviors as well as overall urban traffic dynamics and will be validated against real data. This project will explore new ways to merge formal methods with optimization-based MDP and SG synthesis for decision-making policies that incorporate unique set of specifications at an individual and ensemble level. Formal methods techniques allow for qualitative specifications (e.g., access, fairness, etc.) to be encoded into objectives for which the proposed correct-by-design innovations will lead to provable guarantees needed to ensure sustainable policy development. Finally, with collaborators at the Seattle DOT, experimental trials that go beyond data collection will be conducted in selected Seattle commercial districts to test and validate designed control and parking policy changes.