Two PhD scholarships are currently available:
1. Real-time Analytics on Urban Trajectory Data for Road Traffic Management
This PhD project is part of an Australian Research Council (ARC) Linkage project titled “Real-time Analytics on Urban Trajectory Data for Road Traffic Management”. The overall aim of this ARC Linkage project is to develop real-time analytics and data management capabilities that leverage large-scale urban trajectory data to provide road operators with real-time insights into population movements and enable data-driven, customer-centric network operations. Current traffic management practices rely heavily on aggregate vehicle count data from fixed road sensors, which have limitations in accurately measuring traffic demand and network congestion propagation. We seek to develop innovative technologies to use a wide variety of data sources, especially massive trajectories of vehicles moving across the network, to better understand people’s travel demands and road usage patterns and thus better manage the transport system. The successful applicant will work as a team with researchers from UQ Transport Engineering Group within the School of Civil Engineering and UQ Data Science Research Group within the School of Information Technology and Electrical Engineering, as well as industry partners from Queensland Department of Transport and Main Roads (TMR) and Transmax Pty Ltd. The successful applicant will have flexibility to enrol through either the School of Civil Engineering or the School of Information Technology and Electrical Engineering.
2. Data-driven Modelling of Urban Traffic Networks using Spatial Trajectory Data
This PhD project is part of an Australian Research Council (ARC) project titled “Data-driven Simulation of Large Traffic Networks using Trajectory Data”, which aims to provide transport planners and operators with a smart decision support tool that enables automated insight generation and data-driven decision making. This project will develop an innovative traffic simulation platform that builds a traffic simulation model directly from data by inferring urban mobility patterns and behavioural rules underlying travellers’ decisions from large-scale vehicle trajectory datasets. The project tasks include the implementation of various machine learning technologies (including deep learning and reinforcement learning) to model interactions between vehicles and road networks and predict drivers’ route choice behaviours and network traffic dynamics. The successful applicant will enrol through the School of Civil Engineering.
If you are interested in any of these projects, please contact email@example.com for more details.