Conference Sessions
Keynote Session 3 — Nikolas Geroliminis
Title: On the Inefficiency and Management of Ride-Sourcing Services towards Urban Congestion
Speaker: Nikolas Geroliminis
Abstract: Human mobility in congested city centers is a complex dynamical system with high density of population, many transport modes to compete for limited available space and many operators that try to efficiently manage different parts of this system. New emerging modes of transportation, such as ride-hailing and on-demand services create additional opportunities, but also more complexity. Little is known about to what degree its operations can interfere in traffic conditions, while replacing other transportation modes, or when a large number of idle vehicles is cruising for passengers. We experimentally analyze the efficiency of TNCs using taxi trip data from a Chinese megacity and an agent-based simulation with a trip-based MFD model for determining the speed. We investigate the effect of expanding fleet sizes for TNCs, passengers’ inclination towards sharing rides, and strategies to alleviate urban congestion. We observe that, although a larger fleet size reduces waiting time, it also intensifies congestion, which, in turn, prolongs the total travel time. Such congestion effect is so significant that it is nearly insensitive to passengers’ willingness to share and flexible supply. Finally, parking management strategies can prevent idle vehicles from cruising without assigned passengers, mitigating the negative impacts of ride-sourcing over congestion, and improving the service quality. We are also developing different type of control strategies, such as relocation of empty vehicles, parking management and pricing incentives to alleviate the negative effects.
Break
Break
T‑4: Regular Session/Behavior — Mingyou Ma
Submission: Quantifying Day-to-Day Evolution of Choice Patterns in Public Transit System with Smart Transit Card Data
Presenter: Mingyou Ma
Authors: Mingyou Ma (UNSW Sydney)*; Wei Liu (University of New South Wales); Xinwei Li (Beihang University); Fangni Zhang (UNSW Sydney); Sisi Jian (); Vinayak Dixit (UNSW)
T‑1: Regular Session/Emerging Mobility — Yingyan Lou
Submission: Congestion Mitigation for Planned Special Event: Smart Parking, Ride-Sharing Drop-off Locations and Network Configuration
Presenter: Yingyan Lou
Authors: Jun Xiao (Arizona State University); Yingyan Lou (Arizona State University)*
T‑2: Regular Session/Freight — Tanvir Ahamed
Submission: Deep Reinforcement Learning for Crowdsourced Urban Delivery: System States Characterization, Heuristics-guided Action Choice, and Rule-Interposing Integration
Presenter: Tanvir Ahamed
Authors: Tanvir Ahamed (University of Illinois at Chicago); Bo Zou (University of Illinois at Chicago)*; Nahid Farazi (University of Illinois at Chicago); Theja Tulabandhula (UIC)
T‑3: Regular Session/Data — Zijian Hu
Submission: Self-Calibration of Traffic Surveillance Camera Systems for Traffic Density Estimation on Urban Roads
Presenter: Zijian Hu
Authors: Zijian Hu (The Hong Kong Polytechnic University); Wei Ma (The Hong Kong Polytechnic University)*; William Lam (The Hong Kong Polytechnic University); S. C. Wong (The University of Hong Kong); Andy Chow (City University of Hong Kong)
T‑6: Lightning Session/Traffic Operations — Zhanguo Song
Submission: Short-Term Traffic Flow Uncertainty Prediction Using an Improved Grey Prediction Model under Different Time Intervals
Presenter: Zhanguo Song
Authors: ZHanguo Song (Southeast University)*; Xiao Qin (University of Wisconsin-Milwaukee)
T‑6: Lightning Session/Traffic Operations — Rongsheng Chen
Submission: Traffic Assignment Analysis of Traffic Networks with Max-Pressure Control
Presenter: Rongsheng Chen
Authors: Rongsheng Chen (University of Minnesota)*; Michael W. Levin (University of Minnesota)
T‑6: Lightning Session/Traffic Operations — Rui Okuhara
Submission: Effect of Traffic Accident on Arterial Road Network
Presenter: Rui Okuhara
Authors: Rui Okuhara (Ehime Univercity)*; Toshio Yoshii (Ehime University); Takahiro Tsubota (Ehime university); Hirotoshi Shirayanagi (Ehime University)
T‑6: Lightning Session/Traffic Operations — Md Abu Sayed
Submission: Predict Short-Term Traffic Flow with Prediction Error from Traffic Sensor Data Using Deep Learning
Presenter: Md Abu Sayed
Authors: Md Abu Sayed (University of Wisconsin-Milwaukee)*; Xiao Qin (University of Wisconsin-Milwaukee)
T‑6: Lightning Session/Traffic Operations — Monika Filipovska
Submission: Computation and Estimation of Path Travel Time Variability with Sparse Vehicle Trajectory Data
Presenter: Monika Filipovska
Authors: Monika Filipovska (Northwestern University); Hani S. Mahmassani (Northwestern University)*
T‑5: Lightning Session/Emerging Mobility — Aurore Sallard
Submission: Modeling Ride-Hailing Use in Megacities: Evidence from São Paulo
Presenter: Aurore Sallard
Authors: Aurore Sallard (IVT, ETHZ)*; Milos Balac (IVT, ETHZ); Kay W. Axhausen (IVT, ETH)
T‑5: Lightning Session/Emerging Mobility — Qianwen Li
Submission: Autonomous Vehicle Identification Based on Car-Following Data
Presenter: Qianwen Li
Authors: Qianwen Li (University of South Florida)*; Xiaopeng Li (University of South Florida); Handong Yao (University of South Florid)
T‑5: Lightning Session/Emerging Mobility — Evangelos Mintsis
Submission: Management of Connected and Automated Vehicle Disengagements in the proximity of Work Zones
Presenter: Evangelos Mintsis
Authors: Evangelos Mintsis (Hellenic Institute of Transport (HIT))*
T‑5: Lightning Session/Emerging Mobility — Rafaqat Ali
Submission: A Multimodal Traveling Itinerary Problem in a Time Dependent Multimodal Transportation Network for a Fixed Sequence of Nodes with Time Windows
Presenter: Rafaqat Ali
Authors: Rafaqat Ali (Tsinghua University)*
T‑5: Lightning Session/Emerging Mobility — Huimin Yan
Submission: Coordinated Space-Time Trajectory Planning and Cyclic Control in Automated Vehicle Zones
Presenter: Huimin Yan
Authors: Huimin Yan (Tsinghua University)*
T‑6: Lightning Session/Traffic Operations — Lukas Vacek
Submission: Discontinuous Galerkin Method for Macroscopic Traffic Flow Models on Networks using Numerical Fluxes at Junctions
Presenter: Lukas Vacek
Authors: Lukáš Vacek (Charles University)*; Václav Kučera (Charles University)
T‑4: Regular Session/Behavior — Hebert Azevedo-Sa
Submission: Using Trust in Automation to Enhance Driver-(Semi)AutonomousVehicle Interaction and Improve Team Performance
Presenter: Hebert Azevedo-Sa
Authors: Hebert Azevedo Sa (University of Michigan)*
T‑1: Regular Session/Emerging Mobility — Amirmahdi Tafreshian
Submission: Proactive Vehicle Dispatching in Large-Scale Ride-Sourcing Systems
Presenter: Amirmahdi Tafreshian
Authors: Amirmahdi Tafreshian (University of Michigan)*; Mojtaba Abdolmaleki (University of Michigan); Neda Masoud (University of Michigan); Huizhu Wang (Ford Motor Company)
T‑2: Regular Session/Freight — Sudheer Ballare
Submission: A Many-to-Many Vehicle Routing Problem with Split Loads
Presenter: Sudheer Ballare
Authors: Jane Lin (University of Illinois at Chicago)*; Sudheer Ballare (University of Illinois at Chicago)
T‑3: Regular Session/Data — Ang Li
Submission: Within-Day Prediction of Path Travel Times with Use of Multi-Source of Traffic Data
Presenter: Ang Li
Authors: Ang Li (The Hong Kong Polytechnic University)*; William Lam (The Hong Kong Polytechnic University); Renxin Zhong (Sun Yat-sen University)
T‑4: Regular Session/Behavior — Ragavendran Gopalakrishnan
Submission: Behavioral Models of Users in Ride-Sharing
Presenter: Ragavendran Gopalakrishnan
Authors: Theja Tulabandula (University of Illinois at Chicago)*; Ragavendran Gopalakrishnan (Queens University)
T‑1: Regular Session/Emerging Mobility — Kenan Zhang
Submission: A General Spatiotemporal Equilibrium Model of Ride-Hail Market
Presenter: Kenan Zhang
Authors: Yu (Marco) Nie (Northwestern University)*; Kenan Zhang (Northwestern University)
T‑2: Regular Session/Freight — Mausam Duggal
Submission: Unknown to Known: Predicting Truck GPS Commodity Using Machine Learning
Presenter: Mausam Duggal
Authors: Mausam Duggal (WSP); Bryce W Sharman (WSP)*; Rick Donnelly (WSP); Matthew Roorda (University of Toronto); Sundar Damodaran (Ministry of Transportation of Ontario); Shan Sureshan (Ministry of Transportation of Ontario)
T‑3: Regular Session/Data — Di Yang
Submission: Exploring the Possibility of Outlier Detection Using Functional Data Analysis for Proactive Safety Management
Presenter: Di Yang
Authors: Di Yang (New York University)*; Kaan Ozbay (New York University); Kun Xie (Old Dominion University); Hong Yang (Old Dominion University); Fan Zuo (New York University); Di Sha (New York University)
T‑4: Regular Session/Behavior — Zhengtian Xu
Submission: Understanding Ride-Sourcing Drivers’ Customer-Search Behavior
Presenter: Zhengtian Xu
Authors: Junji Urata (University of Michigan)*; Jintao Ke (Hong Kong University of Science and Technology); Zhengtian Xu (University of Michigan); Guojun Wu (Worcester Polytechnic Institute); Yafeng Yin (University of Michigan); Hai Yang (Hong Kong University of Science and Technology); Jieping Ye (Didi Chuxing)
T‑1: Regular Session/Emerging Mobility — Min Xu
Submission: Addressing the Fleet Sizing Problem for Shared-and-Autonomous-Mobility Services
Presenter: Min Xu
Authors: Min Xu (The Hong Kong Polytechnic University)*
T‑2: Regular Session/Freight — Guoqing Zhang
Submission: An Integrated Location-Inventory Model for the Healthcare Supply Network under Stochastic Demands
Presenter: Guoqing Zhang
Authors: Guoqing Zhang (University of Windsor)*; Mohammed Almanaseer (University of Windsor); Xiaoting Shang (University of Windsor)
T‑3: Regular Session/Data — Xiangyang Guan
Submission: Correcting Biases in Using Emerging Big Data for Mobility Research: A Likelihood-Based Approach
Presenter: Xiangyang Guan
Authors: Xiangyang Guan (University of Washington)*; Cynthia Chen (University of Washington); Shuai Huang (University of Washington)
Break
Break
Keynote Session 4 — Alexandre Bayen
Title: Lagrangian Control at Large and Local Scales in Mixed Autonomy Traffic Flow
Speaker: Alexandre Bayen
Abstract: This talk investigates Lagrangian (mobile) control of traffic flow at local scale (vehicular level). The question of how self-driving vehicles will change traffic flow patterns is investigated. We describe approaches based on deep reinforcement learning presented in the context of enabling mixed-autonomy mobility. The talk explores the gradual and complex integration of automated vehicles into the existing traffic system. We present the potential impact of a small fraction of automated vehicles on low-level traffic flow dynamics, using novel techniques in model-free deep reinforcement learning, in which the automated vehicles act as mobile (Lagrangian) controllers to traffic flow. Illustrative examples will be presented in the context of a new open-source computational platform called FLOW, which integrates state of the art microsimulation tools with deep-RL libraries on AWS EC2. Interesting behavior of mixed autonomy traffic will be revealed in the context of emergent behavior of traffic: https://flow-project.github.io/