Transport for London (TfL) is trialling the use of artificial intelligence (AI) to better plan and operate new cycle routes in the capital.
Until now, TfL has relied mainly on manual traffic counts to work out how many people are cycling on any given road. This helps assess demand for new cycle routes and supports TfL in planning how it operates the road network for the growing numbers of people cycling.
Manual traffic counts, which are carried out at limited locations on London’s road network, are only able to give a snapshot of road use on the given day or time.
Since 2018, TfL has been trialling sensors from Vivacity Labs at two busy locations. The sensors use AI to detect road users and decide which mode of transport they are using. The trial found that the Vivacity sensors are up to 98 per cent more accurate than manual methods.
The trial found that the Vivacity sensors are up to 98 per cent more accurate than manual methods.
The sensors gather data 24 hours a day for a much more detailed picture of how London’s roads are being used throughout the day and night.
As well as accurately detecting people cycling, the sensors also detect people walking and other types of traffic, including cars, HGVs, vans, motorcyclists and buses. This could lead to a much better understanding of demand on the road network and how TfL can balance it.
Glynn Barton, TfL’s director of network management, said: “We work around the clock to keep people in London moving and we’re always looking for innovative new ways of making our roads safer and more efficient. New data from trials such as this will be really valuable as we invest and make day-to-day decisions to enable more people to walk and cycle.”
The sensors are part of a wider programme of modernisation of TfL’s current road network systems and have the potential to link up to London’s traffic signals and control centre systems to provide data in real-time, which could enable TfL to better balance demand and improve how it manages congestion.