Skip to the content

Follow us @UKAuthority

Greater Cambridge Partnership pilots AI traffic controls

12/03/21

Mark Say Managing Editor

Share

Some of the busiest road junctions in Cambridge are to be used in trials of AI traffic signals in an attempt to reduce congestion and improve air quality.

Woman on bike approaching road junction

The Greater Cambridge Partnership (GCP) – consisting of the local city and county councils along with South Cambridgeshire District Council and the university – is funding the 12-month project to be run by Vivacity AI Labs.

It will investigate how camera based sensors and machine learning be used to optimise signals to improve traffic flow and reduce the emissions caused by idling vehicles.

This part of a wider package of measure to be discussed by the GCP board later this month.

Claire Ruskin, executive board member of the GCP and chair of the Smart Cambridge Working Group, said: “We know our traffic lights need to be more intelligent and we are finding new technology solutions that can help the way people make their daily journeys. 

“These new sensors can monitor different types of road users, and use that data to change traffic flows, potentially helping to cut congestion and improve air quality. We will use the data to inform future projects and interventions.”

Potential for prioritisation

The majority of traffic signals across Cambridgeshire currently use fixed algorithms to make decisions in their operation. Vivcity said that AI sensors installed in the cameras are more able than existing systems to anonymously identify different types of road users and adjust traffic signal timings accordingly, which allows different modes of transport to be prioritised.

Installation of the sensors began this week at four locations, and the trial is successful the GCP will consider further investments.

Image from Greater Cambridge Partnership

 

Register For Alerts

Keep informed - Get the latest news about the use of technology, digital & data for the public good in your inbox from UKAuthority.