Active Computing & AI Engineering

Artificial Intelligence for Autonomic Urban Traffic Control

Funder UKRI
Recipient organisation University of Huddersfield
Funding £595K
Period Feb 2025 — Jan 2028

In plain English

AI plain-English summary

The average UK commuter loses 115 hours each year sitting in traffic, costing the economy more than £8 billion annually. Current traffic control systems rely on simplified models and can only react to problems after they occur—they cannot handle today’s unpredictable, post-pandemic travel patterns or the growing number of vehicles. This project will build an artificial intelligence framework that takes a holistic view of an entire urban region’s traffic conditions, then proactively adjusts signals, routes, and flows to prevent congestion and reduce emissions before they happen. If successful, the system could transform how cities manage movement—not just for cars, but for connected autonomous vehicles, buses, cyclists, and pedestrians. Instead of traffic lights that respond only to what has already gone wrong, the AI would anticipate demand shifts and coordinate infrastructure in real time. The result would be less time wasted in jams, lower greenhouse gas output, and reduced health impacts from vehicle pollution. This is applied engineering research with a direct, measurable goal: make urban traffic control smarter, faster, and forward-looking rather than reactive.

View original technical description
More than half of the world's population now resides in cities, and global urbanisation continues at a steady pace. This trend exacerbates mobility issues, with the average UK citizen losing 115hrs annually to traffic congestion, with an estimated annual cost to the economy of more than £8bn. Furthermore, urban traffic poses a significant health threat and is a major contributor to greenhouse gases. Currently deployed traffic control techniques are unable to cope with the increased traffic demand and the highly unpredictable post-pandemic traffic patterns, as they rely on simplified traffic models and operate in a purely reactive mode. The use of Artificial Intelligence, coupled with the wide availability of data, large-scale interconnectivity, and emerging modes of transport such as Connected Autonomous Vehicles, can trigger a shift from reactive to proactive urban traffic control. By leveraging new and complementary AI approaches, the proposed line of research aims to design and develop an urban traffic management and control framework with a holistic view of the controlled region's conditions. This framework will enable proactive actions to prevent environmental and mobility issues, while also supporting effective operations to mitigate observed problems.

View the original record at the funder ↗

Researchers

Mauro Vallati (Principal Investigator)

Related Research

Grants with similar aims, by meaning.

SimplifAI
Transfer Learning Solutions for Intelligent Transportation
Using Machine Learning and AI to explore potential systems for costing and managing Mobility as a Service and Transport Infrastructure
Advanced traffic flow theory and control for heterogeneous intelligent traffic networks
Improved Traffic Signal Control through Individual Vehicle Position Data

Original classification

Fellowship

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.