Research Projects
Updated Oct 2015

Lead Investigator: Christopher ZEGRAS (MIT)
The FM IRG will focus on the following three cross-cutting, and inter-dependent research “themes”, which further develop the seminal work done in the first phase of the project both in terms of scope and depth:

Theme 1: People and Urban Mobility will seek to understand what drives and shapes the demand for mobility both by individuals and by businesses, and how the availability of transportation affects their life choices such as housing, work, and educational or recreational options.

MIT Investigator(s): Moshe BEN-AKIVA (LEAD), Joseph FERREIRA, Emilio FRAZZOLI, Marta GONZALEZ, Li-Shiuan PEH, Christopher ZEGRAS, Jinhua ZHAO
Develop and integrate state-of-the-art behavioral models with simulation tools to predict the impact of different mobility portfolios, including flexible mobility on demand services and autonomous mobility, on travel demand and activities, both for passengers and freight, and on transportation networks and land-use.

LIVE Singapore! 2.0
MIT Investigator(s): Carlo RATTI (LEAD), Marta GONZALEZ, Patrick JAILLET, Daniela RUS
A platform for the collection, fusion, distribution and visualization of real-time data from different sources in Singapore that can serve as the active application of a semantic web platform to the management of the city, and form the basis for crowd sourced open application development.

Future Mobility Sensing (FMS)
MIT Investigator(s): Christopher ZEGRAS (LEAD), Moshe BEN-AKIVA, Daniela RUS
Development of a next generation individualized mobility sensing system that leverages advanced mobile technologies and machine learning techniques to capture high resolution, multi-day human behaviour and vehicular and freight movements as well as related preferences and satisfaction information.

Activity Recognition and Automatic Surveys
MIT Investigator(s): Daniela RUS (LEAD), Carlo RATTI, Christopher ZEGRAS
Using data from sensor streams such as GPS and camera sensors associated with users, we will identify the activity sequence of the users.

Mobility Management
MIT Investigator(s): Jinhua ZHAO (LEAD), Moshe BEN-AKIVA, Joseph FERREIRA, Christopher ZEGRAS, Emilio FRAZZOLI, Patrick JAILLET

Topic 1: Advanced Transport Pricing (ATP)
Enhancing transport pricing with information technology and behavioral economics, including 1) first-best pricing using comprehensive mobility sensing, 2) salience in transportation pricing, and 3) congestion pricing with autonomous vehicles

Topic 2: Mobility Clearing House (MCH)
Design and build a mobility clearinghouse that responds to dynamic and heterogeneous consumer preferences, absorbs emerging mobility technology & business models, and establishes a communication protocol and implementation platform for mobility service exchange

Topic 3: Emotional Travel and Transport Policy (ETTP)
Incorporate emotional and psychological aspects of travel behavior in transportation policy design, including normative and image motivations for policy compliance, the impact of individual's frame of reference on perceived fairness, and a behavioral framework for policy acceptance.

Theme 2: Real-time traffic estimation and control will enable better exploitation of real-time information that could help traffic operators to increase network-wide capacity and reduce travel times, and help travelers in making better decisions.

Infrastructure-less ITS with next-generation devices
MIT Investigator(s): Li-Shiuan PEH (LEAD), Eytan MODIANO
Most ITS systems today require the deployment of costly physical roadside infrastructure such as gantries, traffic signals, signs, and sensors embedded within the fixed transportation infrastructure. As a result, deployment and maintenance of ITS systems remains highly costly, and tends to be limited to selected regions rather than island-wide. Next-generation devices will comprise sufficient computing, networking, sensing hardware to enable the realization of truly infrastructure-less ITS, realized entirely with on-board or handheld devices. In this project, we seek to go beyond off-the-shelf hardware, leveraging next-generation mobile devices, sensors, actuators and radios for prototyping future ITS.

DynaMIT 2.0
MIT Investigator(s): Moshe BEN-AKIVA (LEAD)
Develop a multi-modal network state estimation and prediction system that utilizes heterogeneous real-time data from a variety of sources to assess the impact of congestion-causing planned and unplanned events and optimize interventions/network management strategies to facilitate the real-time deployment of measures to mitigate congestion.

Data-driven, traffic-aware, real-time routing
MIT Investigator(s): Patrick JAILLET (LEAD), Saurabh AMIN, Emilio FRAZZOLI, Carlo RATTI, Daniela RUS
Algorithms that use real-time data from many heterogeneous sources in order to (i) track and predict paths in dynamic transportation networks, and (ii) provide on-demand route guidance under uncertainty, based on a combination of optimization, data-fusion, machine learning, and novel behavioral techniques.

Next-generation Traffic Control
MIT Investigator(s): Emilio FRAZZOLI (LEAD), Saurabh AMIN, Eytan MODIANO, Li-Shiuan PEH, Jinhua ZHAO
Develop an optimal vehicle traffic management system and the corresponding autonomous control mechanism so that the transportation infrastructure can support the maximum amount of traffic with minimal traffic congestion throughout the system. Such a system is likely to include mechanisms for traffic scheduling, routing, and flow control.

Cyber-physical security of transportation networks
MIT Investigator(s): Saurabh AMIN (LEAD), Emilio FRAZZOLI, Patrick JAILLET
Develop tools to detect and proactively respond to incidents in networked transportation systems, both reliability failures (random faults) and security failures (malicious attacks). Our approach involves modeling strategic attacker-defender interactions using game-theoretic tools, and combining incentive mechanisms with network control strategies to improve the transportation network resilience, even in the presence of simultaneous cyber-physical failures.

Theme 3: Demand-responsive mobility will develop new approaches and new algorithms to ensure that supply and demand for mobility are matched to the maximum extent.

Public Transportation Analytics, Planning, and Control
MIT Investigator(s): Jinhua ZHAO (LEAD), Emilio FRAZZOLI

Topic 1: Embedding TNC in Public Transportation
Envision a public transportation system that embeds Transport Network Companies such as UBER and Lyft, including pricing integration, ticketing technology integration, customer information integration, and service planning integration.

Topic 2: Individualized Information Provision (IIP)
Deep individualization of customer information to nudge travel behavior, in combination with pricing incentives to address peak hour crowding problems.

Topic 3: Demand prediction and planning for large events
We apply web mining and machine learning techniques to better predict transit demand for large events (or aggregations of several small ones) in Singapore. Predictions help understand capacity constraints and plan ahead weeks or months in advance. (Collaborator: Francisco C PEREIRA)

Topic 4: Improving arrival time predictions using confidence intervals
We apply conditional quantile regression techniques to determine the reliability of each arrival time prediction. This research also concerns to understand, from the point of view of the user, how such information should be presented and how much it influences decision making. (Collaborator: Francisco C PEREIRA)

Mobility on Demand
MIT Investigator(s): Emilio FRAZZOLI (LEAD), Saurabh AMIN, Moshe BEN-AKIVA, Edgar BLANCO, Marta GONZALEZ, Patrick JAILLET, Carlo RATTI, Daniela RUS, Christopher ZEGRAS, Jinhua ZHAO
Develop models and algorithms to configure dynamically portions of the public transportation service network to meet mobility demands in real- time; the objective is to provide passenger-centric, timely service while minimizing costs and maximizing system efficiency.

Safe and Affordable Autonomy
MIT Investigator(s): Emilio FRAZZOLI (CO-LEAD), Daniela RUS (CO-LEAD), Jonathan HOW, Sertac KARAMAN
Assess and demonstrate the role of autonomy in mobility-on-demand and its impact in terms of feasibility, safety, and efficiency through modelling and simulation, algorithm development and experimental demonstration.

Driverless Singapore
MIT Investigator(s): Emilio FRAZZOLI (LEAD), Arnold BARNETT, Daniela RUS, Carlo RATTI, Sertac KARAMAN,
Jonathan HOW, Jinhua ZHAO
Understand the role of autonomous cars in the context of “car-lite mobility”, and investigate how this technology will change the face of future cities and the lives of their residents.