Student Seminar by Mr. Runqiu Hu on Jun 30, 2025 2PM

Title: Repositioning in bike sharing systems with broken bikes considering on-site repairs

Speaker: Mr. Runqiu Hu (Department of Civil Engineering)

Date: Jun 30, 2025 (Monday)

Time: 2:00 pm - 3:00 pm

Venue: Room 612B, 6/F, Haking Wong Building, The University of Hong Kong

About the talk: This research introduces a novel approach to bike-sharing system operations by simultaneously considering both vehicle-based repositioning and on-site repairs of broken bikes. While existing studies have typically assumed broken bikes can only be repaired at depots after collection, this research recognizes that bike-sharing operators also dispatch repairers for on-site repairs, satisfying demand without vehicle repositioning. A mixed-integer linear programming model is developed for a static bike repositioning problem combining vehicle-based delivery/collection with labor-based on-site repairs, aimed at minimizing the total cost of user dissatisfaction and carbon emissions within a specified time budget. For efficient solution of this complex problem, a hybrid algorithm is proposed incorporating Genetic Search with Adaptive Diversity Control and a novel Station Budget Constrained heuristic, which limits time spent at each station based on benefit-cost ratios. Computational experiments demonstrate that the algorithm obtains optimal solutions for small instances and outperforms commercial solvers on larger networks with less computational time. The cost-effectiveness of deploying repairers is examined, revealing diminished effectiveness with longer repair times and lower percentages of broken bikes. These findings highlight the need for dynamic repairer allocation based on the system's actual damage level, suggesting preventive maintenance strategies can reduce both broken bikes and repair time. The study contributes to the understanding of how on-site repairs can be integrated with traditional repositioning methods in bike-sharing systems.

About the speaker: Mr. Runqiu Hu is currently a Ph.D. student in the Department of Civil Engineering at The University of Hong Kong, supervised by Prof. W.Y. Szeto. He received his bachelor’s degree in Cybersecurity from the Department of Computer Science, Nanjing University of Posts and Telecommunications in 2018 and master’s degree in Computer Technology from the School of Computer Science and Engineering, Southeast University, China, in 2021. His research interests include shared mobility systems, transportation optimization, multi-objective optimization, and the application of artificial intelligence in transportation engineering. Runqiu has publications in several journals including Transportation Research Part E, Transportation Research Part D, IEEE Internet of Things Journal, and IEEE Access. His work focuses on bike-sharing system operations, electric vehicle range anxiety analysis, and intelligent transportation optimization. During his master’s study, he developed expertise in knowledge representation and reasoning, particularly in non-monotonic reasoning for decision support systems using answer set programming and finding reasoning paths for the explainable AI. His current research explores the integration of operations research techniques with transportation engineering challenges, with a specific emphasis on developing efficient algorithms for complex optimization problems in shared mobility contexts.

18 Jun 2025 (Wed) 15:00-16:00 | Seminar by Dr. Fan ZHU & Mr. Feifei SU (Baidu Apollo)

Apollo Go: Driving the Future with Innovation

Speaker:

Dr. Fan ZHU & Mr. Feifei SU

Baidu Apollo International

Date:    Jun 18, 2025 (Wed)

Time:   3:00 pm – 4:00 pm

Venue:  Room 612B, 6/F Haking Wong Building, The University of Hong Kong

Abstract

Baidu Apollo’s robotaxi marks a significant step in the advancement of autonomous driving and intelligent mobility. The seminar aims to provide an overview of how autonomous driving is becoming integrated into daily life and its potential to enhance transportation systems. The progress and vision behind Apollo Go’s robotaxi service, along with the technologies supporting its development, will also be introduced.  The discussion will also highlight future trends in autonomous vehicle technology and Baidu Apollo’s globalization strategy, with Hong Kong identified as one of the first international destinations. By sharing these developments, Baidu Apollo seeks to encourage thoughtful conversation about the role of innovation in shaping the future of urban transportation and the ways these advancements could benefit communities in Hong Kong and beyond.

About the Speakers

Dr. Fan ZHU is the Principal Architect of Baidu's Intelligent Driving Group (IDG). With over a decade of experience in artificial intelligence and autonomous driving, he brings extensive research and project expertise to the field. After earned both his master's and PhD degrees from the University of Edinburgh, UK, he completing his postdoctoral fellowship at the University of Michigan. In 2015, he joined Baidu's US division and became a founding member of Baidu IDG. Fan has published more than 20 papers in prestigious journals such as Nature Methods, Nature Communications, and Bioinformatics. Additionally, he holds over 170 US patents and more than 110 patents granted in China.

SU Feifei is Baidu Apollo’s Senior Product Manager and Technology Evangelist. SU is a Master graduate from Flinders University, Australia, a member of the Data Systems and Simulation Committee of the China Simulation Federation, as well as a member of the Artificial Intelligence and Robotics Committee of the China Education Development Strategy Society.  He serves as an external innovation mentor at several universities, including Beijing Institute of Technology, Jilin University, University of Science and Technology Beijing, Yanshan University etc.. SU is also an external Masters Degree supervisor at Beijing Technology and Business University and Chongqing University of Arts and Sciences.  Currently, SU is mainly responsible for building the developer ecosystem for Baidu Apollo’s Autonomous Driving Open Platform.  He has participated in the compilation of several teaching materials, including “Data Communication and Network Technology”, “Robot Operating System”, “Introduction to Intelligent Connected Vehicles”, “Intelligent Connected Vehicle Perception Technology” and “Intelligent Connected Vehicle Integration and Testing”.

Student Seminar by Ms. Fangyi Ding on May 23, 2025 10AM

Title: A Graph Deep Learning Model for Station Ridership Prediction in Expanding Metro Networks

Speaker: Ms. Fangyi Ding (Department of Urban Planning and Design)

Date: May 23, 2025 (Friday)

Time: 10:00 am - 11:00 am

Venue: Room 612B, 6/F, Haking Wong Building, The University of Hong Kong

About the talk: Due to their reliability, efficiency, and environmental friendliness, metro systems have become a crucial solution to transportation challenges associated with urbanization. Many countries have constructed or expanded their metro networks over the past decades. During the planning stage, accurately predicting station ridership post-expansion, particularly for new stations, is essential to enhance the effectiveness of infrastructure investments. However, station-level metro ridership prediction under expansion scenarios (MRP-E) has not been thoroughly explored, as most advanced models currently focus on short-term predictions. MRP-E presents significant challenges due to the absence of historical data for newly built stations and the dynamic, complex spatiotemporal relationships between stations during expansion phases. In this study, we propose a Metro-specific Multi-Graph Attention Network model (Metro-MGAT) to address these issues. Our model leverages multi-sourced urban context data and network topology information to generate station features. Multi-relation graphs are constructed to capture the spatial correlations between stations, and an attention mechanism is employed to facilitate graph encoding. The model has been evaluated through realistic experiments using multi-year metro ridership data from Shanghai, China. The results validate the superior performance of our approach compared to existing methods, particularly in predicting ridership at new stations.

About the speaker: Fangyi Ding is currently a PhD candidate in the Department of Urban Planning and Design at the University of Hong Kong (HKU). She holds a master's degree from Tongji University and a bachelor's degree from the Harbin Institute of Technology. Her research interests lie in transportation demand forecasting, network modeling, and travel behavior analysis, with a particular focus on public transit and shared mobility services. Her work has been published in leading academic journals and conferences, including Transportation Research Part D, the Journal of Transport Geography, the Transportation Research Board (TRB) Annual Meeting, and ACM SIGSPATIAL, among others.