Collaborative Research: CPS: Medium: An Online Learning Framework for Socially Emerging Mixed Mobility

新兴的交通系统，如互联和自动化车辆以及共享交通，为用户提供了最有趣的机会，使他们能够更好地监控交通网络状况，并做出更好的决策，以提高安全和交通效率。然而，交通网络中不同程度的车辆自动化可以显著改变交通效率指标（旅行时间、能源、环境影响）。此外，我们预计高效交通可能会改变人类的出行行为，产生反弹效应，即通过提高效率，出行成本降低，从而增加出行意愿。后者将增加车辆行驶的总里程，这反过来又可能抵消能源和旅行时间方面的好处。该项目将把新兴的交通系统和模式与现实世界的数据和处理过的信息结合起来，形成一个具有广泛经济、环境和社会效益的公平的交通系统。我们希望这个项目的成果能够增进我们对反弹效应、旅行需求和容量的变化、人员接收、采用和使用新兴移动系统的理解。这项研究的结果将提供一个在线学习框架，旨在在给定的交通网络中分配旅行需求，从而产生一个旅行者愿意接受的社会最优移动系统。“社会最优出行系统”被定义为：(1)在能源消耗和出行时间方面是高效的，(2)不产生反弹效应，(3)确保交通公平的出行系统。该框架将通过合并学习和控制方法来建立优化控制网络物理系统的新方法。它包括开发新方法，以提高交通运输的可达性、安全性和公平性以及旅客的接受度。在提出的框架背景下，“社会计划者”面临的问题是，当旅行者的私人信息不为公众所知时，将旅行者的偏好汇总成一个集体的、全系统的决策。利用机制设计理论推导出所有出行者的最优路线和交通方式的选择，以最大限度地提高交通的可达性、安全性、公平性和出行者的接受度。在线学习算法将会被开发出来，用于识别旅行者的偏好，并确定他们会如何回应社会规划师关于路线和交通模式选择的建议。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Emerging mobility systems, e.g., connected and automated vehicles and shared mobility, provide the most intriguing opportunity for enabling users to better monitor transportation network conditions and make better decisions for improving safety and transportation efficiency. However, different levels of vehicle automation in the transportation network can significantly alter transportation efficiency metrics (travel times, energy, environmental impact). Moreover, we anticipate that efficient transportation might alter human travel behavior causing rebound effects, e.g., by improving efficiency, travel cost is decreased, hence willingness-to-travel is increased. The latter would increase overall vehicle miles traveled, which in turn might negate the benefits in terms of energy and travel time. The project will consolidate emerging mobility systems and modes with real-world data and processed information leading to an equitable transportation system with broad economic, environmental, and societal benefits. We expect the outcome of this project to enhance our understanding of the rebound effects, changes in travel demand and capacity, human reception, adoption, and use of emerging mobility systems. The outcome of this research will deliver an online learning framework that will aim at distributing travel demand in a given transportation network resulting in a socially-optimal mobility system that travelers would be willing to accept. A “socially-optimal mobility system” is defined as a mobility system that (1) is efficient (in terms of energy consumption and travel time), (2) does not cause rebound effects, and (3) ensures equity in transportation. The framework will establish new approaches in optimally controlling cyber-physical systems by merging learning and control approaches. It includes the development of new methods to enhance accessibility, safety, and equity in transportation and travelers’ acceptance. In the context of the proposed framework, a “social planner” faces the problem of aggregating the preferences of the travelers into a collective, system-wide decision when the private information of the travelers is not publicly known. Mechanism design theory will be used to derive the optimal routes and the selection of a transportation mode for all travelers so as to maximize accessibility, safety, and equity in transportation and travelers’ acceptance. Online learning algorithms for contextual bandit problems will be developed to identify traveler preferences and to determine how they would respond to the social planner’s recommendations on routing and selection of a transportation mode.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.