Enhanced coupling approach to demand prediction and repositioning in shared autonomous vehicle systems

Organised by: RCE 2

Abstract:

The integration of autonomous vehicles (AVs) into car-sharing services offers significant advantages, including reduced labor costs, increased vehicle utilization, and more efficient fleet management. In such shared autonomous vehicle systems (S-AVS), efficient and adaptive vehicle repositioning plays a crucial role in meeting time-varying traffic demand, typically achieved by leveraging user demand prediction. However, most existing studies treat traffic demand prediction and shared autonomous vehicle (SAV) scheduling as separate tasks, ignoring the tight interaction between the two components, potentially leading to inaccurate predictions and less efficient repositioning performance.

This presentation will introduce our recent work on an enhanced coupling design for Demand prediction and Repositioning for shared autonomous Vehicle system. Two corresponding coupling strategies are designed, differentiated by their respective coupling locations. We also consider the scenario of a mixed fleet, which includes both AVs and human-driven vehicles, balancing operating profit with fairness considerations.

Bio of invited speaker:

Dr. Dongyao Jia is currently an Associate Professor at the School of Advanced Technology, XJTLU, and an Honorary Senior Research Fellow at the University of Queensland. He received the PhD degree in Computer Science from the City University of Hong Kong in 2014. Prior to joining XJTLU, he worked as a Research Fellow in the School of Civil Engineering, the University of Queensland, from 2018 to 2021, and the Institute for Transport Studies, University of Leeds, the UK from 2015 to 2018, respectively. He also holds a ten-year working experience in the telecom industry in China. In the past few years, he has been actively involved as the PI or co-PI in several research projects funded by National Science Foundation of China, EU H2020, etc. His main research interests include connected and automated driving, traffic flow modelling and optimization, and digital-twin-enabled transportation.