Student Seminar by Ms. Luyun Zhao on Oct 14, 2025, 1PM

Title: Strategic planning for public transportation electrification: large-scale electric bus network transition planning via deep reinforcement learning

Speaker: Ms. Luyun Zhao (Department of Urban Planning and Design)

Date: Oct 14, 2025 (Tuesday)

Time: 1:00 pm - 2:00 pm

Venue: Room 8-28, Haking Wong Building, The University of Hong Kong

Registration Link: https://forms.office.com/r/FThKpBgpfp

ITS Student Committee will provide light refreshments and drinks for registered participants.

Abstract: Urban bus electrification is gaining global interest, playing a crucial role in reducing emissions. This study defines and addresses the electric bus network transition problem (EBNTP), jointly optimizing battery electric bus (BEB) fleet transitions and charging facility planning over a multi-period horizon. Existing research often neglects this interdependent long-term planning and lacks scalable solutions for large systems. This study proposes a deep reinforcement learning (DRL) approach, formulating EBNTP as a Markov Decision Process modeling sequential planning decisions, and introduces the DRL-HetGNN method, integrating heterogeneous graph neural networks (HetGNN) to capture network effects and enhance efficiency in large-scale applications. Using Hong Kong's franchised bus system as a case study, DRL-HetGNN demonstrates superior performance and generalizability compared to benchmark methods. Scenario analyses explore budget allocations, independent operators, BEB subsidies, and price fluctuations, while examining policy-incentive mechanisms to accelerate electrification. The findings will support policymakers in planning sustainable public transportation systems.

Bios: Luyun Zhao is a PhD candidate at the Department of Urban Planning and Design, Faculty of Architecture, HKU. Her research interest lies in public transit, shared mobility, transportation electrification, and transportation modeling. She has more than five years of theoretical and practical experience in the transportation industry. Prior to HKU, she worked at Tencent Smart Transportation, DiDi Chuxing Public Transportation Department and Two-Wheeler Department, Bytedance, and the World Bank. Luyun received her Bachelor of Engineering and Bachelor of Economics degrees from Peking University and her Master of City Planning degree from the University of Pennsylvania.

30 Sep 2025 (Tue) 11:00-12:15 | Seminar by Prof. Fang He

Strategic Coordination and Integration in Ride-Hailing Platforms

Speaker:

Prof. Fang He

Department of Industrial Engineering

Tsinghua University

Date:    Sep 30, 2025 (Tuesday)

Time:   11:00 am – 12:15 pm

Venue:  Room 8-28, 8/F Haking Wong Building, The University of Hong Kong

Abstract

This seminar synthesizes two complementary game-theoretic investigations that together illuminate how ride-hailing ecosystems can be steered toward greater efficiency and welfare. The first study frames idle drivers’ information-enabled relocation as a multi-stage leader–follower game on arbitrary service networks. The platform (leader) designs relocation subsidies; drivers (followers) relocate and compete for revenue. Existence and uniqueness results show that when volume imbalances are pronounced or commission rates are low, drivers’ self-interested moves already align with system objectives, making relocation-specific subsidies superfluous. In residual cases, spatial–temporal targeted incentives can double platform profit and markedly boost trip completions, with gains amplified on sparse networks and when driver behavior retains moderate stochasticity. The second study examines the rise of third-party integrated platforms (IPs) that match orders across heterogeneous service providers (SPs) under a revenue-sharing commission. A three-stage mixed-integer game reveals that integration outcomes hinge on four interactive forces: relative SP size, demand stimulation, profit redistribution, and commission design. Excessive consolidation dampens competition, discourages large SPs, and allows the IP to over-extract surplus—threatening industry welfare when worker supply is ample. A ceiling-commission policy emerges as an effective regulatory safeguard.

Bio

Dr. Fang He is Deputy Head for Research and Tenured Associate Professor in the Department of Industrial Engineering at Tsinghua University. He serves as the Executive Vice Dean of the Tsinghua University–COSCO Shipping Green & Intelligent Supply Chain Institute. His research focuses on network modeling and optimization, large-scale combinatorial optimization and deep reinforcement learning, producing more than 60 journal papers, including publications in TS (6), Transportation Research Part Series (40+), and POM (3). He serves as the Associate Editor of Transportation Science and the Editor of Transportation Research Part B. Dr. He is also a recipient of a national-level Young Talent Program in China, and his scholarly work has been implemented by China COSCO Shipping Group, AutoNavi Ride-Hailing, the Beijing 2022 Winter Olympics, and the Wuhan Power Grid, among other high-impact sectors. He has been recognized as an Elsevier Highly Cited Chinese Scholar for six consecutive years (2019–2024), with a single paper exceeding 600 citations. Dr. He received his B.S. degree in Civil Engineering from Tsinghua University in 2010 and his Ph.D. degree from the University of Florida in 2014.

Student Seminar by Dr. Yimo Yan on Sep 29, 2025, 3PM

Title: Event-driven policy optimization for dynamic ambulance dispatch: An attention-based reinforcement learning approach

Speaker: Dr. Yimo Yan (Department of Data and Systems Engineering)

Date: Sep 29, 2025 (Monday)

Time: 3:00 pm - 4:00 pm

Venue: Room 8-28, Haking Wong Building, The University of Hong Kong

Registration Link: https://forms.office.com/r/nvWGefbq5n

ITS Student Committee will provide light refreshments and drinks for registered participants.

Abstract: The global healthcare strain from events such as the COVID-19 pandemic has intensified ambulance shortages, leading to prolonged patient waiting times and increased mortality. In this respect, efficient ambulance dispatch presents a backbone for providing timely patient care. This paper tackles the problem of dynamic ambulance dispatch as a semi-Markov decision process, with the objective of minimizing severity-weighted waiting times through en-route re-dispatching and event-driven decisions. We propose a policy gradient algorithm with a self-attention approximator, which enables inter-task (patients) and inter-agent (ambulances) communications under uncertainty and variable inputs. To further enable interpretability, we distill the learned policy into a decision tree with theoretically grounded features. Experiments on synthetic and real-world cases demonstrate reduced average waiting time and its variance for patients, improved ambulance operational efficiency, and effective use of strategic withholding. Our approach contributes to the development of interpretable, rule-based ambulance dispatch systems in resource-constrained medical environments.

Bios: Dr. Yimo Yan graduated from the Department of Data and Systems Engineering at The University of Hong Kong in Aug 2025. Yimo’s work focuses on transportation and logistics optimisation, incorporating methods like mixed integer linear programming, reinforcement learning, deep learning and large language model. His research, published in various academic journals, addresses challenges in last-mile delivery and scheduling.