AI optimisation for transport corridor performance

The aim of the project is to leverage AI algorithms and machine learning to optimise the performance of motorways, arterials, and ramps in cities, by predicting future traffic speed and proactively responding to them.

This will help create a more efficient transportation network for the movement of goods and people between urban and suburban areas within a city, for work and leisure.

The project will model the road network and seek to optimise travel time proactively tailored to and tested with Melbourne datasets.

Participants

• Cubic Transportation Systems
• University of Melbourne

Project background

The project will be a Virtual AI-driven TMC (traffic management control) to become an innovative research and development initiative aimed at revolutionising transportation network management through the use of cutting-edge.
artificial intelligence (AI) and machine learning (ML) technologies.

The project is focused on retrofitting an AI-powered platform that can predict and mitigate traffic congestion, queue length, and air quality issues on corridors and related routes between state and national roads, thereby optimising the performance of transportation systems.

The project is designed to address the increasingly complex challenges associated with managing modern transportation networks in urban and suburban areas. Traffic congestion, accidents, and environmental pollution are some of the major issues that negatively impact the efficiency and sustainability of transportation systems, leading to frustration, inconvenience, and even health problems for commuters and residents alike.

By leveraging AI and ML technologies, this project aims to provide real-time insights into traffic patterns, predict speed, and optimise traffic flow to create a more efficient and sustainable transportation network.

Project objectives

The primary goal of this project is to establish a state-of-the-art AI-based platform for transport network management that is data-integrated, capable of predicting speed and optimised for performance.

The first phase of the program will involve testing/retrofitting/training the models and using them as an evaluation platform throughout the program to refine and improve their accuracy and effectiveness based on Melbourne datasets.

The project will also focus on improving the understanding of the complex relationship between congestion on arterials, ramps, and motorways, and how to address incidents and improve performance to minimise traffic delays and prevent accidents.

By leveraging advanced AI and ML technologies, the project aims to create a smarter and more efficient transportation network that can provide real-time insights and optimise traffic flow based on a wide range of data inputs and sources.

Overall, this project is an exciting and ambitious initiative that has the potential to enhance transportation network management in Melbourne and other cities worldwide, promoting efficiency, sustainability, and liveability for urban
and suburban communities.

Specifically, the project’s objectives are to:

• evaluate the use of AI technology to enhance corridor performance, focusing on arterials, ramps, and motorways;
• analyse the relationships between multiple modes of transportation, road user types, and the capacity of different segments on a journey, while prioritising ease of travel and journey time;
• optimise movement and evaluate the execution approach required to improve it;
• refine the model performance for the complex city of Melbourne, generating actionable outcomes and integrating additional data inputs; and
• enhance transport network management, leading to a reduction in traffic congestion, improved air quality, and a better experience for road users.

Please note …

This page will be a living record of this project. As it matures, hits milestones, etc., we’ll continue to add information, links, images, interviews and more. Watch this space!