Lead Investigator: Professor Emilio FRAZZOLI (MIT)
The FM IRG is structured around three pillars, designed to advance the state-of-the-art in critical areas:
Pillar 1: Networked Computing and Control (NCC) will seek to develop a framework of common, re-usable services and algorithms, packaged as software libraries and run-time software infrastructure for urban mobility systems.
Application-Guided Network Design
MIT Project Leader: Professor Li-Shiuan PEH
Design new programming models and middleware, along with novel applications, that can harness many phones as a collaborative computing platform for directly hosting transportation services.
Autonomy in Mobility-on-Demand Systems
MIT Project Leader: Professor Emilio FRAZZOLI with Professor Daniela RUS
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.
Real-Time Control and Learning for Urban Transportation Systems
MIT Project Leader: Professor Emilio FRAZZOI with Professor Daniela URS
Development of new tools, combining real-time, distributed control techniques, systems and control theory, and machine learning to develop new approaches to the design of urban transportation systems. Examples include traffic signal control and scheduling, road pricing, and resilience analysis under disruption.
Car-Speak: A Communication System Customized for Autonomous Driving
MIT Project Leader: Professor Dina KATABI with Professor Daniela RUS
Enable a car query and access sensory information captured by other cards in a manner similar to how it accesses information from its local sensors.
Congestion-Aware Routing for Urban Mobility
MIT Project Leader: Professor Daniela RUS with Professor Patrick JAILLET
Develop, implement, and evaluate novel decentralised control algorithms for individual participants in urban traffic; algorithms should provide stability and global behaviour guarantees under different types of traffic scenarios, by combining machine learning and control techniques.
MIT Project Leaders: Professor Carlo RATTI and Dr. Kristian KLOECKL
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.
Pillar 2: Integrated modelling of mobility, land-use, environmental, and energy-use impacts will develop a suite of powerful demand estimation, performance prediction, and operation optimisation tools, drawing on the availability of NCC-enabled information.
Integrated Simulation Platform: SimMobility
MIT Project Leader: Professor Moshe BEN-AKIVA with Professors Emilio FRAZZOLI, Patrick JAILLET, Li-Shiuan PEH, Christopher ZEGRAS and Joseph FERREIRA
Integrate and link together various mobility-sensitive behavioural models with state-of-the-art simulators to predict impacts of mobility demands on transportation networks, services and vehicular emissions. Integration will make it possible to simulate the effects of a portfolio of technology, policy and investment options under alternative future scenarios.
Real-Time Model System for Network Management and Emergency Response
MIT Project Leader: Professor Moshe BEN-AKIVA (MIT) with Professors Patrick JAILLET, Amedeo ODONI and Daniela RUS
Develop an integrated suite of models to estimate the impact of alternative interventions and support the real-time deployment of such interventions to mitigate urban mobility problems as they occur on a daily basis.
Real-time Path Tracking/Predictions and On-Demand Route Guidance Under Uncertainty
MIT Project Leader: Professor Patrick JAILLET with Professor 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.
Mobility on Demand: Dynamic, Demand-Responsive Transportation Service Network Design
MIT Project Leader: Professor Cynthia BARNHART with Professor Amedeo ODONI
(a) 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; (b) The Last Mile Problem: Explore innovative ways for transporting travellers between home or work and a preferred node of the public transportation system, taking advantage of information and communications technologies, real-time route planning, and light (possibly semi-autonomous) urban vehicles; (c) Examine impact on MRT users of disruptions at different parts of the network. Design recovery from MRT disruptions that minimize inconvenience to MRT users.
Pillar 3: Performance assessment and implementation will enable more meaningful evaluation of alternative sustainability mobility systems and the development of institutional, regulatory, and pricing mechanisms to support them.
Real-Time Regulation of Mobility Services
MIT Project Leader: Professor Christopher ZEGRAS with Profesoor Joseph FERREIRA
Cheap and abundant data streams generated by modern mobility systems hold the promise of changing regulatory and policy making frameworks to enable more efficient, effective, intermodal mobility services, with greater transparency and accountability. The potential uses of ITS automated data in regulators, transport operators, planners, and the public raise a number of questions related to: data access and ownership, new types of performance measures, contractual relationships, appropriate regulatory structures, and structuring incentives for mobility innovations. Key initial sub-projects include: critical evaluation of international approaches to data-driven regulation; assessment of the relationship between data and contract structure in the current regulatory scheme in Singapore; and investigation of the feasibility of integrated, regulation-oriented performance measurement and forecasting.
Behavioural Models for Land Use, Mobility and Energy and Resource Use
MIT Project Leader: Professor Moshe BEN-AKIVA with Professors Joseph FERRERIA and Christopher ZEGRAS
To plan sustainable future urban mobility systems, we need a set of forecasting tools to help make well-informed, consistent assessments of future conditions under various scenarios. Behavioral models are at the heart of the approach. The objective is to develop state-of-the-art models to understand and forecast different behavioral rationales of households and firms.
Development and Testing of Network-Enabled Data Collection Techniques
MIT Project Leader: Professor Moshe BEN-AKIVA with Professor Christopher ZEGRAS
The ubiquity technologies related to Networked Computing and Control (NCC) provides a range of new close-to-real-time data for urban mobility planning and management. The objective here is to implement a broad data collection effort using smart phones matched with web-based surveying tools to infer (through machine learning) household and firm activities, including mobility and location choices.