NSF Convergence Accelerator Track H: Leveraging Human-Centered AI Microtransit to Ameliorate Spatiotemporal Mismatch between Housing and Employment for Persons with Disabilities

残疾人（PWD）在历史上面临着重大的就业挑战，主要是由于缺乏前往就业相关兴趣点（ePOI）的交通工具，如工作，教育和培训地点。提供门到门和路边到路边服务的辅助客运服务可以缓解第一/最后一英里的问题。然而，他们往往需要提前几天到几周提交收件请求，这不够灵活，无法处理更紧急的请求，以按时到达ePOI。造成这种时间滞后的一个主要原因是缺乏可获得的技术来帮助作出复杂而迅速的决定，以确定上下车地点、路线、时间安排和重新安排路线。该项目通过提高辅助运输服务的可用性和可靠性，促进残疾人融入工作场所。具体来说，我们的愿景是提供一种开源的以人为本的人工智能（AI）技术，帮助微交通服务确定何时何地接送PWD，并结合近实时路由算法，以满足住宅和ePOI丰富地区之间更紧急的PWD请求。该项目将建立在底特律大都会地区的几个组织之间已经建立的强有力的合作基础上，这些组织包括辅助运输服务提供商、残疾研究机构、劳动力发展机构、外联通信服务和韦恩州立大学。具体而言，在本项目中，我们计划：（1）组织外展活动、焦点小组和研讨会，以吸引更多组织参与，进行汇聚利益相关者的讨论，以更好地了解他们的需求，如何最好地提供接近实时的辅助运输服务，以满足已确定的需求，并确定数据和ePOI进行测试;（2）研究跨地区辅助交通服务需求的流入和流出情况，以及所确定的服务区内残疾人的可达性;（3）为每个利益相关者类型（用户、服务提供商、雇主）的原型成功创建衡量工具。该项目产生的数据和测量工具将影响拟议技术的开发和设计。该奖项反映了NSF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。

Persons with disabilities (PWD) have historically faced significant employment challenges mainly due to lack of transportation to employment-related Points of Interest (ePOIs) such as work, education, and training locations. Paratransit services that provide door-to-door and curb-to-curb services could alleviate the first/last mile problem. However, they often require submitting pick-up requests a few days to a few weeks in advance, which is not flexible enough to handle more urgent requests to arrive at ePOIs on time. A main reason for such temporal lags is the lack of accessible technology that helps make complex yet prompt decisions for the determination of pick-up/drop-off location, routing, scheduling, and re-routing. This project promotes disability inclusion in workplaces by enhancing the availability and reliability of paratransit services. Specifically, our vision is to deliver an open-source human-centered Artificial Intelligence (AI) technology that aids microtransit services to determine when and where to pick up/drop off PWD, and incorporates near real-time routing algorithms to serve more urgent PWD requests between residential and ePOI-rich regions. This project will be built on the already established strong collaboration among several organizations operating in the Metro Detroit Area, including paratransit service providers, disability research institutions, workforce development institutions, outreach communication services, and Wayne State University. Specifically, in this project we plan to: (1) Organize outreach activities, focus groups, and workshops to involve more organizations, have a convergent stakeholder discussion to better understand their needs, how best to provide near real-time paratransit services to meet identified needs, and identify data and ePOIs for testing; (2) Study inflow and outflow of paratransit service demand across regions and accessibility for PWD in the identified service area; (3) Create measurement tools for success of our prototype for each stakeholder type (user, service provider, employers). The data and measurement tools generated by this project will shape the development and design of the proposed technology.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.