Introduction
Urban areas are increasingly becoming congested, and existing traffic management systems are ill-equipped to deal with the real-time issues this congestion causes. Cutting-edge interactive data visualisation and machine learning techniques can help to produce a data-driven real-time traffic management system. Such a system could help city planners prepare for the future and manage current conditions, optimising energy consumption and system resilience.
Explaining the science
The UN predicts that by 2030, metropolitan areas are projected to house 60% of the world’s population. Cities themselves are also changing with an increase in ridesharing platforms and same-day delivery fleets, which dramatically affect traffic patterns. Moreover, while environmental standards are improving, congestion in urban environments needs to be managed to maintain our health in cities.
Managing traffic and optimising traffic signals within cities has long relied on traditional modelling and forecasting. Real-time events, changing conditions, and evolving mobility patterns mean existing systems can no longer keep pace and adapt to new needs in urban environments.
Project aims
The objective of the project is to transition complex traffic management from static systems into dynamic, optimised systems that cities manage in real-time across many types of mobility.
There are a number of ways researchers and software engineers on this project aim to tackle this challenge:
- Integrating an AI system for traffic lights (signal) control.
- Building a platform for interactive data manipulation to monitor and predict traffic behaviour, and to test out planning scenarios.
- Finding mechanisms for fleet operators and cities to work together, for example by sharing data about congestion or pollution hotspots, and rerouting around the problem before it becomes serious.
The work is an 18-month, £650k+ collaboration between the Turing and Toyota Mobility Foundation, and is part of the Turing’s programme in artificial intelligence. Researchers will also be working with data providers, and government managers underpinning future cities, as well as drawing upon expertise from the Turing and partner universities’ ongoing work in the area with the Greater London Authority, and mobility expertise within the Toyota Mobility Foundation.
Applications
By combining real-time operations with periodic monitoring and long-term planning, outcomes of the project will be useful to urban planners as they manage current conditions in cities and prepare for the future.
A data-driven traffic management system should help optimise air quality, reduce energy consumption, and improve system capacity and resilience.
The study of how fleets and cities might work together will also contribute to the ongoing debate about the role of regulation and data-sharing.
Organisers
Collaborators
Researchers and collaborators
