ACTIVITY2025

4 Mar 2026 (Wed) 17:00-18:00 | Distinguished Industrial Seminar by Mr. WANG Ning

Apollo Go: Driving the Future with Innovation

Speaker:

Mr. WANG Ning

Baidu Apollo International

Date: Mar 4 (Wed), 2026

Time: 5:00pm – 6:00pm

Venue: Tam Wing Fan Innovation Wing Two, G/F Run Run Shaw Building, HKU

Registration: https://forms.office.com/r/3CMJ2ehD2c

Prof. W.Y. Szeto introducing the Institute of Transport Studies

Prof. Yong-Hong Kuo introducing the speaker of the distinguished industrial seminar, Mr. WANG Ning.

Group photo - Mr. WANG Ning and all audience

Group photo - Mr. WANG Ning, his colleagues, and ITS Fellows

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 speaker

Mr. Ning WANG is a Senior Product Specialist at Baidu Apollo, where he leads the integration and large‑scale deployment of Apollo Go’s 6th‑generation Robotaxi (RT6) and he has played a key role in delivering multiple industry‑first milestones in autonomous mobility.

Mr. Wang holds a Master’s degree in Information Technology and Sensor Systems from the Technical University of Darmstadt in Germany. With nearly a decade of R&D and product leadership experience across China and Germany, including prior roles as Product Director at Momenta and Audi AG, he brings deep expertise in autonomous driving algorithms, data closed‑loop systems, and vehicle software integration. At Baidu Apollo, he is committed to bridging cutting‑edge AI research with real‑world, at‑scale industrial applications, advancing the commercialization of robotaxis and next‑generation intelligent driving solutions.

17 Dec 2025 (Wed) 17:00-18:00 | Seminar by Dr. Beatriz Martinez-Pastor

Designing Smart and Resilient Transport Systems

(The lecture slides can be downloaded here)

Speaker:

Dr. Beatriz Martinez-Pastor

School of Civil Engineering

University College Dublin

Date: Dec 17, 2025 (Wednesday)

Time: 5:00 pm – 6:00 pm

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

Abstract

This presentation introduces the core principles of designing smart and resilient transport systems, emphasising how data-driven methods, user-centred approaches, and climate-adaptive strategies can enhance the robustness and inclusivity of future mobility networks. It then highlights three key initiatives. The SETO project advances the smart enforcement of transport operations across the EU, creating a digital platform that integrates data from diverse sources and provides seamless access to regulation-related information. The platform ensures high levels of data security by adopting state-of-the-art industry standards and blockchain technology, enabling an innovative, efficient, consistent, and resilient enforcement support system for multimodal and cross-border contexts. The CAPABLE national project develops a digital platform to assess community capability-based resilience, placing communities at the centre of infrastructure system decision-making and supporting more inclusive and adaptive planning. The NBSINFRA European project applies nature-based solutions to enhance the resilience, sustainability, and social value of transport infrastructure, safeguarding critical urban assets against both natural and human-induced hazards. Together, these projects demonstrate how technological innovation, community-centred methods, and nature-based strategies can be combined to create transport systems that are intelligent, inclusive, and highly adaptable.

About the speaker

Dr. Beatriz Martinez-Pastor is an Assistant Professor in the School of Civil Engineering at University College Dublin (UCD), and the Director of the Centre for Critical Infrastructures Research. Between 2021 and 2025, she was the Director of the Civil Engineering Infrastructure programme at Chang’an-Dublin International College, CDIC, UCD. She completed her Ph.D. at Trinity College Dublin, and her MSc. at the University of Cantabria. Since then, she has specialized in the evaluation of transportation resilience, digital transformation of transport systems, intelligent transport systems, and analysis of complex systems. Dr. Martinez-Pastor has coordinated two Horizon Europe projects, SETO (Smart Enforcement of Transport Operations, €4 million and 14 partners), and the CSA for organising TRA2024 (€1.5 million and 15 partners). Dr. Martinez-Pastor is the PI of a Horizon Europe project, NBSINFRA (€5 million and 17 partners), the PI and Academic leader of STRADA and STRADA2, a European project to develop a Leadership programme for women in engineering, the Co-PI of a SFI project, CAPABLE (Resilience Challenge) and is the co-leader of the transport strand in a large national project, NEXSYS. Dr. Martinez-Pastor has managed over 7 million in research funds and published over 50 papers in peer-review journals and conferences.

19 Dec 2025 (Fri) 14:00-15:00 | Seminar by Prof. Dongfang Ma

Dynamic Ice Field Perception and Panoramic Map Generation for Polar Navigation

Speaker:

Prof. Dongfang Ma

Ocean college, Zhejiang University

Date: Dec 19, 2025 (Friday)

Time: 2:00 pm – 3:00 pm

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

Abstract

Safe and efficient polar navigation requires high-precision, real-time panoramic ice maps across long voyages. Yet conventional visual mapping techniques struggle in this environment due to sparse surface textures, severe six-degree-of-freedom ship motion during icebreaking, and long-term accumulated drift. To address these challenges, we present a two-stage visual mapping framework designed for the dynamics of polar ice fields.

First, we introduce a single-epoch construction method based on motion-compensated inverse projection. Initial inverse projection uses INS pose estimation to support feature registration, followed by a refined inverse projection optimized through bundle adjustment to mitigate view distortion induced by violent ship motion. Building upon this foundation, we then propose a multi-epoch incremental mapping strategy that integrates hybrid feature matching with a sliding window filter. Embedding GPS constraints within the sliding window effectively suppresses accumulated drift and ensures global pose consistency throughout extended navigation sequences.

From single-frame correction to globally consistent map generation, this work delivers a complete solution for robust visual perception in highly dynamic polar environments.

About the speaker

Ma Dongfang, male, Ph.D., Professor, Ocean college, Zhejiang University, and a reserve leader in the construction industry in Zhoushan. He is mainly engaged in the research and practice of marine data mining, intelligent control theory and methods, and internet of things. He graduated from Jilin University in June 2012 with a Ph.D. degree in traffic information engineering and control. He joined the postdoctoral research station of civil engineering at Zhejiang University in the same year as a postdoctoral researcher. In July 2015, he joined Ocean University of Zhejiang University as a teacher. As project leader, he has presided over the National Natural Science Foundation of China, the Natural Science Foundation of Zhejiang Province, the China Postdoctoral Science Fund Project, and the China National Postdoctoral Fund Special Funding Project, Zhejiang Province key science and technology innovation team project, the Ministry of Education Humanities and Social Science Fund project. Published about 20 SCI journal papers (the first and correspondent authors).