Alleviating Bus Bunching via Modular Vehicles

Abstract

The notorious phenomenon of bus bunching prevailing in uncontrolled bus systems produces irregular headways and downgrades the level of service by increasing passengers’ expected waiting time. Modular autonomous vehicles (MAVs), due to their ability to split and merge en route, have the potential to help both late buses and early buses recover from schedule deviation while providing continuous service. In this seminar, Dr Chen proposes a novel bus bunching alleviation strategy for MAV-aided transit systems. He first establishes a continuum approximation model to capture the system dynamics intertwined with the MAV splitting and merging operations, and then establishes an infinite-horizon stochastic optimization model to determine the optimal splitting and merging strategy. Based on the characteristics of the problem, he develops  a customized deep Q-network (DQN) algorithm with multiple relay buffers and a penalized ruin state to optimize the strategy for each MAV bus. Numerical results show that the strategy obtained via the DQN algorithm is an effective bunch-proof strategy and has a better performance than the myopic strategy for MAV-aided systems and the two-way –looking strategy for conventional bus systems. Sensitivity analyses are also conducted to examine the effectiveness and benefits of the proposed strategy across different operation scenarios. 

Speaker

Dr Zhibin Chen is an Assistant Professor of Engineering, New York University Shanghai; Global Network Assistant Professor, New York University. Prior to this appointment , he was a research fellow in the Department of Civil and Environmental Engineering at the University of Michigan, Ann Arbor. Dr Chen’s research goal is to identify, develop, and implement emerging technologies to achieve a safer, more efficient, and environment-friendly transportation system. He was the recipient of the Stella Dafermos Best Paper Award and the Ryuichi Kitamura Paper Award at the 95th TRB Annual Meeting.