Research Initiation Award: Automated Distribution of Autonomous Vehicles

研究启动奖为历史悠久的黑人学院和大学的初级和职业生涯中期教师提供支持，这些教师正在建立新的研究计划或重新定向和重建现有的研究计划。预计该奖项有助于进一步提高教师的研究能力和有效性，改善所在机构的研究和教学，并让本科生参与研究经验。该奖项授予佛罗里达农业与机械大学(FAMU)，支持工业工程方面的研究。更具体地说，它支持有助于研究与自动驾驶汽车分布有关的问题的研究。此外，该项目邀请本科生参与研究活动。总体项目目标是开发和评估一种新的方案，将成品汽车从汽车制造商分配给经销商，前提是自动驾驶技术已经为市场做好了准备。这个项目的动机是一个巨大的文献空白：自动驾驶汽车(AV)技术对自动驾驶汽车本身分发的影响尚不清楚。这种新的分配方案需要较大的AVs(即自动运营商)和较小的AVs(即成品汽车)的协作，这可以通过在不同的AVs之间进行路由成本权衡来带来显著的好处。项目组提出了自动承运人装卸问题的空间状态网络流公式和算法；开发了基于学习的算法来预测给定自动承运人路线的装载可行性和装卸成本；设计了一个完全集成的自动承运人装卸路线优化算法，包括有无AV技术。管理洞察力将通过广泛的计算实验产生，这可以为汽车制造商制定具有成本效益的汽车分销计划提供信息。该项目通过聘请本科生作为学生研究人员，并将该项目的研究成果与PI教授的两门课程相结合，促进了FAMU工程学学生在运筹学和机器学习方面的学术追求。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

Research Initiation Awards provide support for junior and mid-career faculty at Historically Black Colleges and Universities who are building new research programs or redirecting and rebuilding existing research programs. It is expected that the award helps to further the faculty member's research capability and effectiveness, improves research and teaching at the home institution, and involves undergraduate students in research experiences. The award to Florida Agricultural and Mechanical University (FAMU) supports research in industrial engineering. More specifically, it supports research that contributes to research questions pertaining to the distribution of autonomous vehicles. Furthermore, the project engages undergraduate engineering students in the research activities.The overall project goal is to develop and evaluate a novel scheme for distributing finished vehicles from automobile manufacturers to dealers, assuming that self-driving technology is market ready. This project is motivated by a substantial literature gap: the implications of autonomous vehicle (AV) technologies for the distribution of AVs themselves are not yet understood. This novel distribution scheme requires the collaboration of larger AVs (i.e., auto-carriers) and smaller AVs (i.e., finished automobiles), which can bring significant benefits through the routing cost tradeoff between heterogeneous AVs. The project team proposes a space-state network flow formulation and algorithm for the auto-carrier loading and unloading problem; develop learning-based algorithms to predict the loading feasibility and the loading/unloading cost for a given auto-carrier route; design a fully integrated auto-carrier loading and routing optimization algorithm, with and without AV technologies. Managerial insights will be generated through extensive computational experiments, which can inform automobile manufacturers in making cost-effective automobile distribution plans. The project facilitates the preparation of engineering students at FAMU for academic pursuits in operations research and machine learning by engaging undergraduates as student researchers, and through the integration of research findings from this project with two courses taught by the PI.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.