Skip to the content

TfL harnesses AI in planning for cyclists


Transport for London (TfL) has said it is beginning to use artificial intelligence in planning and operating cycle routes around the city.

It has been working with London based tech firm Vivacity Labs on the use of video sensors with an internal AI capability to detect different modes of transport – including cycling and walking – and collecting data that can feed into assessing demand for new cycle routes.

Trials at two locations on Millbank – a main road beside the River Thames – that began in 2018 have shown that the sensors are up to 98% accurate and provide a more in-depth picture than the manual traffic counts on which TfL has previously relied.

This has prompted the authority to begin introducing 43 more sensors at 20 locations around central London to further test the capabilities. It will use the data from these and other sources to plan new cycling infrastructure.

TfL said that all the video captured is processed and discarded within seconds, with no personal data being stored.

Operational potential

In addition, the sensors can be linked to London’s traffic signals and control centre systems to provide real time data to support operations.

Glynn Barton, TfL’s director of network management, said: “We work around the clock to keep people on 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 mayor of London has a transport strategy target for 80% of journeys around the city to be made by walking, cycling or public transport by 2041.

Image from TfL

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.