Predictive Analytics and Real-time Traffic Control for Urban Corridors. This project aims to develop predictive data analytics and real-time traffic control and safety models for multimodal management of urban corridors, serving two salient objectives: (1) optimising person-throughput of multimodal traffic; while (2) minimising safety risks for all modes. The outcome will be an automated, sensor-based platform to monitor traffic flows from all modes and make proactive and coordinated control dec ....Predictive Analytics and Real-time Traffic Control for Urban Corridors. This project aims to develop predictive data analytics and real-time traffic control and safety models for multimodal management of urban corridors, serving two salient objectives: (1) optimising person-throughput of multimodal traffic; while (2) minimising safety risks for all modes. The outcome will be an automated, sensor-based platform to monitor traffic flows from all modes and make proactive and coordinated control decisions in real-time. The expected benefits are profound; the developed algorithms and platform will significantly reduce traffic congestion, travel delays and safety risks for all modes of transport, especially for vulnerable road users (e.g. pedestrians and cyclists).Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE190101020
Funder
Australian Research Council
Funding Amount
$357,000.00
Summary
Data-driven simulation of large traffic networks using trajectory data. This project aims to develop a low-cost, data-driven framework that builds a traffic simulation model automatically and directly from vehicle trajectory data to enable rapid and reliable analysis of large-scale traffic networks. The project expects to generate new knowledge in the area of transport engineering using an innovative approach to inferring travel behaviours, movement patterns and traffic dynamics from increasingl ....Data-driven simulation of large traffic networks using trajectory data. This project aims to develop a low-cost, data-driven framework that builds a traffic simulation model automatically and directly from vehicle trajectory data to enable rapid and reliable analysis of large-scale traffic networks. The project expects to generate new knowledge in the area of transport engineering using an innovative approach to inferring travel behaviours, movement patterns and traffic dynamics from increasingly available urban trajectory data. Expected outcomes include improved decision support for urban planners and traffic operators and enhanced traffic management and incident response capabilities, providing significant social, economic and environment benefits through optimised road use and urban flow.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE160100449
Funder
Australian Research Council
Funding Amount
$336,000.00
Summary
Modelling mixed traffic of traditional, connected, and automated vehicles. This project plans to address the challenge of efficiently operating mixed traffic flow of traditional, connected and automated vehicles. The rapid advancement of technologies is currently turning connected and automated vehicles from science fiction into science fact. However, there are no existing traffic flow models capable of reproducing features of mixed traffic flow consisting of traditional, connected and automated ....Modelling mixed traffic of traditional, connected, and automated vehicles. This project plans to address the challenge of efficiently operating mixed traffic flow of traditional, connected and automated vehicles. The rapid advancement of technologies is currently turning connected and automated vehicles from science fiction into science fact. However, there are no existing traffic flow models capable of reproducing features of mixed traffic flow consisting of traditional, connected and automated vehicles. This project aims to address this knowledge deficit and develop an analytical tool able to accurately model mixed traffic flow. This new knowledge and model are prerequisites to effective operation and control of traffic flow of traditional, connected and automated vehicles.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE220101320
Funder
Australian Research Council
Funding Amount
$425,970.00
Summary
Rethinking traffic modelling for next generation city-scale networks. This project aims to develop an efficient traffic simulation model that enables data-informed traffic monitoring and automated model development, streamlining the fundamental transformation that next-generation cities will undergo in the coming decades. The project expects to generate new knowledge in traffic modelling by developing an innovative approach to inferring traffic conditions and traveller behaviour from diverse dat ....Rethinking traffic modelling for next generation city-scale networks. This project aims to develop an efficient traffic simulation model that enables data-informed traffic monitoring and automated model development, streamlining the fundamental transformation that next-generation cities will undergo in the coming decades. The project expects to generate new knowledge in traffic modelling by developing an innovative approach to inferring traffic conditions and traveller behaviour from diverse data feeds, and automating model calibration through an optimisation formulation. Expected outcomes address the eventual transition to smart cities and connected and autonomous vehicle technologies, providing significant social, economic and environmental benefits through optimal planning and effective operation schemes.Read moreRead less