Future Mobility Lab
Leading the Research Innovation in Smart Cities

The Future Mobility lab (FMlab) in University of Technology Sydney is part of a new Data Science Institute launched in January 2019 by the University of Technology in Sydney under the Faculty of Engineering and IT. The research lab is focusing on developing advanced data driven models for solving some burning real-world problems such as traffic congestion, smart city liveability, mobility fluidity, and transitioning towards new emerging transport modes such as connected and autonomous vehicles, on-demand transport, vehicle-to-vehicle and vehicle-to-infrastructure communications.

The research areas that the lab is working on are spanning from:

The research scientists in this group are using advanced machine learning and smart algorithms to model and improve transport networks, and maximise operational performance. For various planning purposes, the group builds simulation models to analyse the impact of traffic disruptions, signal control changes, etc.

With a strong background in transport modelling and artificial intelligence, the UTS Mobility lab aims to:

The work of the Future Transport Mobility group is aimed at addressing some of the world most challenging problems such as:


Machine Learning for traffic disruptions
Modelling the impact of traffic disruptions such as reported or planned incidents by using data-driven analytics for incident duration prediction and traffic simulation modelling for response plan generation and evaluation
Multi-modal traffic simulation
Modelling various travel demand fluctuations in urban areas by using traffic simulation modelling and traffic assignment at various levels: road, public transport, pedestrians
Public Transport Data Analytics
Modelling real-time public transport performance in terms of delay and travel speed profiling
Traffic flow prediction using A.I.
Applying artificial intelligence to predict how the traffic flow will evolve in the next 5 minutes, 15 minutes, or half an hour into the future, under regular or abnormal traffic conditions
Smart city modelling
Using data science to tackle some of the smart cities problems and building advanced analytical insights in how urban parameters influence our daily travel and life choices
Deep learning for lane-based flow prediction
The purposes of this study are to propose the integrated predictive platform, including model-based and data-driven approaches.
A.I. for car-following models
The objective of this study is to establish a coupled stochastic continuous multi-lane car-following model using Langevin equations to cope with probabilistic characteristics of LC manoeuvre
Personal mobility in mixed traffic
Predicting traffic patterns of personal mobility in real time under heterogeneous traffic conditions
Collaborators
Australian National University, Canberra
Swinburne University of Technology, Melbourne
National Technology University of Singapore
National University of Singapore
ENGSI France
Data61|CSIRO
Fortescue Metal Group
Roads and Maritime Services
Transport for NSW
National Research Foundation Singapore
ITS Australia