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.

Student Seminar by Mr. Dongsheng He on Sep 22, 2025, 3PM

Title: From association to causality: Causal effects of urban transport infrastructure intervention in China using natural experiment approaches

Speaker: Mr. Dongsheng He (Department of Urban Planning and Design)

Date: Sep 22, 2025 (Monday)

Time: 3:00 pm - 4:00 pm

Venue: Room 1010, CLL, Department of Geography, 10/F, The Jockey Club Tower, The University of Hong Kong

Registration Link: https://forms.office.com/r/zrU3BubSh0

Food and drinks will be provided for successfully registered participants.

About the talk: China’s rapid urbanisation has driven extensive construction and expansion of transport infrastructure, notably high-speed rail and intra-city rail transit systems. Such infrastructure projects are characterised by substantial financial investment, long construction timelines, and high sunk costs. Policymakers often assume that these investments generate broad benefits, including economic growth, improved public health, and enhanced social equity. However, most of the current studies rely on cross-sectional observations, which have significant limitations in establishing causal relationships. This seminar introduces a series of large-scale impact assessments of transport infrastructure projects in China, such as urban greenways and metro systems, using natural experiment methods to evaluate their effects on travel behaviours, traffic safety, and housing property values. The findings indicate that the expected benefits of transport infrastructure do not always exist as commonly presumed. Consequently, more nuanced and rigorous evaluations are necessary to better understand the effectiveness and mechanisms of such interventions.

About the speaker: Dongsheng He is currently a PhD candidate in the Department of Urban Planning and Design at the University of Hong Kong. His primary research areas include causal inference of transportation infrastructure impacts, land use and transport integration, and volumetric urban design in high-density cities. He has published more than ten papers in international journals such as Transportation Research Part A/D, Urban Studies, and Landscape and Urban Planning.

2 Sep 2025 (Tue) 17:30-18:30 | Seminar by Dr. Jinwoo Lee

Infrastructure Planning for the Electrification of Public Transit Systems: Cases in Urban Air Mobility, Robotaxis, and Buses

Speaker:

Dr. Jinwoo Lee

Department of Civil and Environmental Engineering

Korea Advanced Institute of Science and Technology (KAIST)

Date:    Sep 2, 2025 (Tuesday)

Time:   5:30 pm – 6:30 pm

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

Abstract

In the effort to reduce greenhouse gas emissions, the transition toward electric and shared mobility systems is widely recognized as a sustainable solution. Among them, deploying electric vehicles in public transit can create synergies that enhance both environmental and social benefits. However, their operations and planning must address the distinctive challenges of electrification, including batteries, charging systems, and supporting infrastructure, in addition to the inherent constraints of public transit. This seminar explores planning problems for electric public transit across three modes: urban air mobility, robotaxis, and buses. These problems are formulated within an optimization framework that incorporates key planning and operational factors specific to each mode’s unique characteristics. Case studies conducted in cities such as Seoul and San Francisco illustrate the proposed optimal planning methods.

Bio

Dr. Jinwoo Lee is an Associate Professor in the Department of Civil and Environmental Engineering at the Korea Advanced Institute of Science and Technology (KAIST). His research focuses on sustainable and intelligent transportation infrastructure systems, with emphasis on planning for shared, autonomous, and electric mobility, AI-driven infrastructure management, and climate change adaptation. Beyond academia, he extends his expertise into practice as Director of Technology Innovation at Studio Galilei, a company providing demand-responsive transit services aimed at advancing inclusive mobility solutions, and as Co-founder and Chief Technology Officer of Rovoroad, which develops AI-robotics-based pavement management technologies. He received his Ph.D. and M.S. in Civil and Environmental Engineering from the University of California, Berkeley, and his B.S. degree from KAIST. Prior to joining KAIST, he worked as a postdoctoral associate at New York University Abu Dhabi and as a research assistant professor at the Hong Kong Polytechnic University.