Funding: Singapore-MIT Alliance for Research and Technology (SMART), 2016-2020
As part of the Future Urban Mobility (FM) IRG of the Singapore-MIT Alliance for Research and Technology (SMART), the team led by Prof. Jinhua Zhao combines behavioral science and transportation technology to envision a future urban mobility system for Singapore that integrates public transit, walking and bicycling, shared mobility, and autonomous vehicles. The current phase of the project consists of four topics: 1. Examining the formation process of people’s preferences for autonomous vehicles (AVs); 2. Monitoring emotional and physiological responses during AV rides; 3. Designing the integration of on-demand AV service with public transport systems; and 4. Social mobility sharing in the interest of joint optimization of network efficiency and preference for human interaction.
Topic #1 Preference Formation for Autonomous Vehicles: Stated Preference Surveys Before and After Actual Trial Rides. The project aims to study the formation process of people's preferences for autonomous vehicles (AVs). In the short term, we will implement multiple stages of stated preference surveys before and after trial rides in AV prototypes to examine how people learn and adapt to new transportation technology in the context of last-mile modal choices.
Topic #2 Electroencephalograph (EEG) and Physiological Measures of Emotional Responses to Autonomous Vehicle using EEG Neuroheadset. The project aims to measure and analyze people’s emotional responses when riding autonomous vehicles in various traffic conditions. We will use an electroencephalograph (EEG) neuro-headset as the main measurement and other physiological measures to corroborate. Link: Emotional Travel
Topic #3 Integrating Autonomous Vehicles with Public Transit Service: Last Mile Service to MRT Stations. The project aims to design and test the new mobility scenarios in which autonomous vehicles are embedded into the public transit system. We will simulate the on-demand last-mile service to and from Singapore MRT stations, testing a variety of business, operation, pricing, and regulation models with different degrees of mixture between autonomous vehicles and public transit services. Link: Governing Autonomous Vehicles
Topic #4 Social Mobility Sharing: Joint optimization of Network Efficiency and Preference for Human Interaction. This project examines dynamic mobility sharing from the perspective of social interaction and develops human-centric ride-sharing systems that respect both network efficiency and individuals’ preferences (or lack thereof) for human interaction. Link: Social Mobility Sharing
|Risk Preferences and Autonomous Vehicles, , Transportation Research Part A, (Submitted)||
While there is an increasingly large body of research on the potential demand for autonomous vehicles (AV), an understudied factor is people’s risk preference. Risk preference is important because many aspects of AVs are highly uncertain as the technology and its encompassing mobility system emerge and continue to evolve. This study analyzed how risk preferences influence the choice of AVs, and how risk preferences elicited by economic and psychometric methods differ in their impacts. We...
|Using Deep Neural Network to Analyze Travel Mode Choice with Interpretable Economic Information: An Empirical Example, , Transportation Research Part C, (Submitted)||
Recently deep neural network (DNN) has been increasingly applied to microscopic demand analysis. While DNN often performs with higher predictive accuracy than traditional multinomial logit (MNL) model, it is unclear whether we can obtain interpretable economic information from DNN-based choice model beyond prediction accuracy. This paper seeks to provide an empirical method of numerically extracting valuable economic information such as choice probability, probability derivatives (or...
|Multitask Learning Deep Neural Network to Combine Revealed and Stated Preference Data, , Transportation Research Part B, (Submitted)||
It is an enduring question how to combine revealed preference (RP) and stated preference (SP) data to analyze travel behavior. This study presents a general multitask learning deep neural network (MTLDNN) to combine RP and SP data and incorporate the traditional nest logit approach as a special case. Based on a combined RP and SP survey in Singapore to examine the demand for autonomous vehicles (AV), we designed, estimated and compared one hundred MTLDNN architectures with three major...
|Framing Discrete Choice Model as Deep Neural Network with Utility Interpretation, , Working paper, (2019)||
Deep neural network (DNN) has been increasingly applied to travel demand prediction. However, no study has examined how DNN relates to utility-based discrete choice models (DCM) beyond simple comparison of prediction accuracy. To fill this gap, this paper investigates the relationship between DNN and DCM from a theoretical perspective with three major findings. First, we introduce the utility interpretation to the DNN models and demonstrate that DCM is one special case of DNN with shallow...
|Mobility Sharing as a Preference Matching Problem, , IEEE Transactions on Intelligent Transportation Systems, (2018)||
Traffic congestion, dominated by single-occupancy vehicles, reflects not only transportation system inefficiency and negative externalities, but also a sociological state of human isolation. Advances in information and communication technology are enabling the growth of real-time ridesharing to improve system efficiency. While ridesharing algorithms optimize passenger matching based on efficiency criteria (maximum number of paired trips, minimum total vehicle-time or vehicle-distance...
|Transit-Oriented Autonomous Vehicle Operation with Integrated Demand-Supply Interaction, , Transportation Research Part C, (2018)||
Autonomous vehicles (AVs) represent potentially disruptive and innovative changes to public transportation (PT) systems. However, the exact interplay between AV and PT is understudied in existing research. This paper proposes a systematic approach to the design, simulation, and evaluation of integrated autonomous vehicle and public transportation (AV+PT) systems. Two features distinguish this research from the state of the art in the literature: the first is the transit-oriented AV operation...
|Integrating Shared Autonomous Vehicle in Public Transportation System: A Supply-Side Simulation of the First-Mile Service in Singapore, , Transportation Research Part A, (2018)||
This paper proposes and simulates an integrated autonomous vehicle (AV) and public transportation (PT) system. After discussing the attributes of and the interaction among the prospective stakeholders in the system, we identify opportunities for synergy between AVs and the PT system based on Singapore’s organizational structure and demand characteristics. Envisioning an integrated system in the context of the first-mile problem during morning peak hours, we propose to preserve high demand...
|Understanding the Usage of Stationless Bike Sharing in Singapore, , International Journal of Sustainable Transportation, (2018)||
A new generation of bike-sharing services without docking stations is currently revolutionizing the traditional bike-sharing market as it dramatically expands around the world. This study aims at understanding the usage of new dockless bike-sharing services through the lens of Singapore's prevalent service. We collected the GPS data of all dockless bikes from one of the largest bike sharing operators in Singapore for nine consecutive days, for a total of over 14 million records. We adopted...
|Distributional Effects of Lotteries and Auctions —License Plate Regulations in Guangzhou, , Transportation Research Part A: Policy and Practice, 11/2017, Volume 106, p.473–483, (2017)||
Lotteries and auctions are common ways of allocating public resources, but they have rarely been used simultaneously in urban transportation policies. This paper presents a unique policy experiment in Guangzhou, China, where lotteries and auctions are used in conjunction to allocate vehicle licenses. Guangzhou introduced vehicle license regulations to control the monthly quota of local automobile growth in 2012. To obtain a license, residents are required to choose between the lottery and...
|Information Effect on Autonomous Vehicle Mode Choice: A Randomized Control Trial Experiment, , Transportation Research Board 97th Annual Meeting, Washington, D.C., (2018)||
This paper studies the effect of negative safety-related information on autonomous vehicle (AV) mode choice in Singapore. The authors implemented a dynamic online survey with half of the subjects receiving negative safety information about AV via a randomized control trial. The authors use a video of Tesla’s fatal crash under autopilot as an approximation of the negative safety information of AV. The authors test the impact of watching this video and its interaction with prior knowledge of...
|An Urban Agenda for Autonomous Vehicles: Embedding Planning Principles into Technological Deployment, , Transportation Research Board 97th Annual Meeting, Washington, D.C., (2018)||
The deployment of autonomous vehicles (AVs) has spawned a considerable literature on the role of national and state-level governments in regulating components of AV manufacturing, emissions, safety, licensing, and data sharing. These provide insight into how AVs can be integrated into the current transportation system. Yet the potential for local governments to shape their futures through AV policies is underexplored. This paper argues that it is both necessary and feasible for...
|Attitudes Toward Effective Time Use in Autonomous Mobility-on-Demand Services in Singapore, , Transportation Research Board 97th Annual Meeting, Washington, D.C., (2018)||
How autonomous vehicles (AVs) may impact passengers’ travel time use is not well understood. Because AVs require minimal attention, users may find themselves free to engage in new activities and use their travel time more effectively. If AVs improve the quality of activities conducted while traveling, passengers may experience reduced value of travel time savings, leading to more and longer trips and thereby increasing congestion and emissions. On the other hand, if people are able to more...
|The Tradeoff Between Efficiency and Fellow Passenger Preference: a Preference-Based Ridesharing Model, , Transportation Research Board 96th Annual Conference, Washington, D.C., (2017)||
Advances in information technology are enabling the growth of real-time ridesharing—whereby passengers are paired up on car trips to improve system efficiency by using fewer cars. Lesser known, however, are the opportunities of shared mobility as a tool to foster and strengthen human interactions. The nature of shared car rides is impromptu, captive for a considerable duration, and remarkably more intimate, representing a unique juxtaposition of spontaneity and intensity. While ridesharing...
|Rebalancing Shared Mobility-on-Demand Systems: a Reinforcement Learning Approach, , IEEE ITSC Workshop on Intelligent Public Transport 2017, (2017)||
Shared mobility-on-demand systems have very promising prospects in making urban transportation efficient and affordable. However, due to operational challenges among others, many mobility applications still remain niche products. This paper addresses rebalancing needs that are critical for effective fleet management in order to offset the inevitable imbalance of vehicle supply and travel demand. Specifically, we propose a reinforcement learning approach which adopts a deep Q network...
|Simulating the First Mile Service to Access Train Stations by Shared Autonomous Vehicle, , Transportation Research Board 96th Annual Meeting, (2017)||
This paper studies the potential impacts of autonomous vehicle (AV) sharing with mobility-on demand service on the public transit system. We analyze the current travel demand in the public transit system in Singapore with a special focus on the first-/last-mile problem during morning peak hours. The first-/last-mile in this paper is defined as the gap between origin/destination and the heavy rail stations. A feasible method to integrate AV sharing in current transit system is proposed, which...
|Enabling Transit Service Quality Co-monitoring Through a Smartphone-Based Platform, , Transportation Research Record: Journal of the Transportation Research Board, (2017)||
The growing ubiquity of smartphones offers public transit agencies an opportunity to transform ways to measure, monitor, and manage service performance. We demonstrate the potential in a new tool for actively engaging customers in measuring satisfaction and co-monitoring bus service quality. The pilot initiative adapted a smartphone-based travel survey system, Future Mobility Sensing (FMS), to collect real-time customer feedback and objective operational measurements on specific bus trips....