报告题目：Optimal Taxi Rebalancing Recommender System

报告人：Prof. Rong Su

报告人单位：新加坡南洋理工大学

报告时间：2024年12月25日（周三）10:00-12:00

会议地点：电气工程与控制科学学院416报告厅（崇德楼D座416）

举办单位：电气工程与控制科学学院

报告人简介：RongSu，教授，博导，新加坡南洋理工大学电气与电子工程学院计算机控制与自动化硕士项目负责人、KTH-NTU 联合博士项目管理委员会 NTU负责人。研究方向包括多智能体系统、离散事件系统理论、基于模型的故障诊断、网络安全分析和综合、复杂网络的控制和优化，以及在柔性制造、智能交通、人机界面、电源管理和绿色建筑中的应用，拥有330多篇期刊和会议出版物、2部专著、18项已授予/申请的专利，曾获得多项最佳论文奖，包括IEEE/CAA Journal of Automatica Sinica 2021年Hsue-shen Tsien论文奖等。 目前，他担任IEEE Transactions on Cybernetics、Automatica (IFAC)、Journal of Discrete Event Dynamic Systems: Theory and Applications和Journal of Control and Decision的副主编。

报告摘要：Ride hailing systems suffer from spatial-temporal supply demand imbalance due to drivers operating in independent, and uncoordinated manner. Several fleet rebalancing models have been proposed that can provide repositioning recommendations to idle standing drivers with the objective of maximizing service rate or minimizing customer waiting time. Existing models assume complete adherence by the drivers which leads to limited practical implementation of these models. A novel taxi rebalancing model and a procedure to compute recommendations for repositioning of taxis are proposed which accounts for uncertainties in adherence arising from taxi driver’s preferences and the evolving confidence of the driver in the system due to outcomes of repositioning recommendations. Extensive simulations using NYC taxi dataset showed that the proposed model can lead to 6.3% higher allocation rates, 11.8% higher driver profits, 4.5% higher demand fulfillment, and 14% higher confidence of drivers’in the rebalancing system, as compared to a state-of-the-art rebalancing model that is agnostic to the taxi driver preferences and confidence in the system

审核人：薄翠梅