The workshop concluded!
Big thanks to our amazing speakers and participants!
About the workshop
With the increasing integration of digital technologies and innovative mobility solutions, network designs aim to enhance the efficiency and safety of transportation networks. Intelligent traffic management systems can collect and process real-time data from diverse sources, including sensors, cameras, and connected vehicles to optimize traffic flow, alleviate congestion, and elevate the overall efficiency of transportation systems. Network designs are engineered with intelligent algorithms that factor in real-time traffic conditions, road incidents, and various other dynamic elements. Dynamic routing and navigation ensures the provision of optimal routes for both drivers and connected vehicles, contributing to a more streamlined and responsive transportation experience. The increasing prevalence of digital connectivity in transportation can also bring forth security challenges. To address emerging security issues, network designs must include robust measures essential to protect sensitive information exchanged within the transportation network.
This workshop aims to create a casual academic environment for researchers, professionals, students, and enthusiasts to interact and exchange ideas. Through engaging talks by invited speakers and interactive discussions, participants will delve into network design challenges, innovative solutions, and gain insights to better understand the complexities and opportunities in the digital mobility era.
Workshop Information
Speaker: 4 invited speakers
Location: Room 1201, 370 Jay Street, Brooklyn, NY
Date: Jan. 16, 2024 (Tuesday)
Host: New York University, New York
Organizers: Prof. Quanyan Zhu, Prof. Kenan Zhang, Ya-Ting Yang
Program Agenda
| Time | Event |
|---|---|
| 09:00 - 09:30 | Prof. Zhibin Chen - NYU Shanghai Topic: Alleviating Bus Bunching via Modular Vehicle Bio and Abstract |
| 09:30 - 10:00 | Prof. Xuan Sharon Di - Columbia University Topic: TBD. Bio and Abstract |
| 10:00 - 10:10 | Coffee Break |
| 10:10 - 10:40 | Prof. Monica Menendez - NYU Abu Dhabi Topic: A Data-Driven Analysis of Urban Traffic Networks Bio and Abstract |
| 10:40 - 11:10 | Prof. Andrea Lodi - Cornell Tech Topic: Machine Learning for Combinatorial Optimization and its Implications to Dynamic Routing Bio and Abstract |
| 11:10 - 12:00 | Discussions |
Registration Form:
https://forms.gle/itcRomsdjNCsNcNj6Please complete the form if you would like to attend the event.
Invited Speakers
Zhibin Chen
Bio
Dr. Zhibin Chen is an Assistant Professor at New York University Shanghai and
Global Network Assistant Professor at New York University. Prior to this
appointment, he was a research fellow at Department of Civil and Environmental
Engineering, University of Michigan, Ann Arbor. Dr. Chen received his Ph.D. in
transportation engineering from the University of Florida in 2017. Dr. Chen’s
research goal is to identify, develop, and implement emerging technologies to
achieve a safer, more efficient, and environment-friendly transportation system. His
research interests include network modeling, discrete optimization, and AI in
transportation. His research has been published in a series of transportation journals
including Transportation Science, Transportation Research Part B/C/D, EJOR, and
IEEE ITS. He was the recipient of the Stella Dafermos Best Paper Award and the
Ryuichi Kitamura Paper Award at the 95th TRB Annual Meeting.
Topic: Alleviating Bus Bunching via Modular Vehicle
Abstract
Modular vehicles are a novel concept that allows for the coupling and decoupling of
different vehicle modules and enables in-motion passenger transfers; it can
potentially increase the flexibility of the transportation system. Recent studies have
numerically highlighted the potential of using modular vehicles as transit buses to
mitigate the bus bunching phenomenon. Building upon this, this study first offers a
comprehensive and systematic analytical assessment of the bunching-proof
capabilities associated with modular buses, and then proposes novel bus bunching
alleviation strategies.
Xuan Sharon Di
Bio
TBD.
Topic: TBD.
Abstract
TBD.
Monica Menendez
Bio
Monica Menendez is the Associate Dean of Engineering for Graduate Affairs
and a Professor of Civil and Urban Engineering at New York University Abu
Dhabi (NYUAD). She is also the Director and Lead PI of the CITIES Research
Center; and the recipient of the NYUAD Distinguished Research Award for
2021. Before joining NYUAD in 2018, Prof. Menendez was the Director of
the research group Traffic Engineering at ETH Zurich. She holds a Ph.D.
(2006) and a M.Sc. (2003) in Civil and Environmental Engineering from UC
Berkeley, and a dual degree in Civil Engineering and Architectural
Engineering (2002) from the University of Miami.
Her research interests include multimodal transportation systems paying
special attention to new technologies and information sources. Prof.
Menendez is a member of multiple editorial boards for top journals in Transportation, and a number of
international organizations, including the International Advisory Committee of the International
Symposium on Transportation and Traffic Theory (ISTTT), and the Mohammed bin Rashid Academy of
Scientists (MBRAS). She is the author of over 100 peer-reviewed journal publications and over 200
conference contributions, book chapters, editorials, and technical reports. In the last five years, five of
the papers that she has co-authored, have received best-paper awards.
Topic: A Data-Driven Analysis of Urban Traffic Networks
Abstract
In this presentation, we will discuss how to bring together concepts from statistical physics and
transportation engineering into a single science of traffic networks, with the goal of improving the
performance of urban traffic, ultimately making our cities more sustainable. We will show that traffic
and the ensuing congestion patterns for any given city are reproducible across days. Hence, it is enough
to monitor the traffic performance of only a few roads to classify daily patterns and the resulting
congestion patterns, allowing cities to reduce monitoring costs. In fact, road and bus network topology
can explain around 90% of the empirically observed variation in network capacity for over 40 cities
around the world. Moreover, it is possible to relate the road level dynamics to the network level
dynamics by observing the number and size of traffic congestion pockets. This allows us to use concepts
from physics (such as percolation) to describe the propagation of congestion, so that we can model it
using sparse network-level data. It also gives us insights into the ability of different networks to cope
with congestion, and the moment at which such congestion becomes so widespread that the whole
network collapses.
Andrea Lodi
Bio
Andrea Lodi is an Andrew H. and Ann R. Tisch Professor at the Jacobs Technion-Cornell Institute at Cornell Tech and the Technion
since 2021. He received his PhD in System Engineering from the University of Bologna in 2000 and he has been Herman Goldstine Fellow
at the IBM Mathematical Sciences Department, full professor of Operations Research at the University of Bologna, and Canada Excellence
Research Chair at Polytechnique Montréal. His main research interests are in Mixed-Integer Linear and Nonlinear Programming and Data
Science. He has been recognized by IBM and Google faculty awards, the 2021 Farkas Prize by the INFORMS Optimization Society and as
2023 INFORMS Fellow. Andrea Lodi has been network coordinator and principal investigator of EU and Canadian projects and consultant
of the IBM CPLEX research and development team (2006-2021).
Topic: Machine Learning for Combinatorial Optimization and its Implications to Dynamic Routing
Abstract
The last decade has witnessed the impressive development of machine learning (ML) techniques - successfully applied to traditional
statistical learning tasks as image recognition and leading to breakthroughs like the famous AlphaGo system. Motivated by those
successes, many scientific disciplines have started to investigate the potential for the use of a large amount of data crunched by
ML techniques in their context. Combinatorial optimization (CO) has been no exception to this trend, and the ML use in CO has been
analyzed from many different angles with various levels of success. In this talk, we briefly review the state of the art of this
scientific path and then we discuss the use of learning for dynamic re-optimization of routing in the context of deliveries in
urban areas. This is an especially promising area with direct implications on optimizing multimodal transportation.