Skip to main content

Vivacity Labs rolls out AI-controlled junctions 

Initiative in Manchester, UK, is designed to facilitate higher levels of non-vehicle movements
By Adam Hill November 13, 2020 Read time: 2 mins
Algorithm can be used to prioritise vulnerable road users at AI-controlled junctions (© Vivacity Labs)

Vivacity Labs has deployed AI-controlled ‘smart’ traffic junctions in Manchester, UK, to enable the increase of active travel modes such as cycling and walking duing the pandemic. 

As more cyclists and pedestrians use junctions originally designed to prioritise cars and other vehicles, there is a need to look carefully at exactly who is using the roads and crossings and how they might most safely be able to move around.

“Since the pandemic, commuter trends and traffic hotspots have changed completely, and cities need AI to help protect people no matter what mode of transport they take,” said Mark Nicholson, CEO of Vivacity Labs. 

“Our vision is to help cities implement critical policies addressing safety, air quality, sustainable travel, and congestion, at a hyper-local level.” 

The programme - which won the Innovative Use of Technology award at the 2020 ITS (UK) Awards - uses sensors with inbuilt AI, enabling Transport for Greater Manchester (TfGM) to anonymously identify different types of road users at selected junctions and control traffic signals.

This means the authority can allow different modes of transportation - including cyclists and pedestrians - to be prioritised as and when required. 

Vivacity says it has developed an algorithm "that is able to adapt quickly to changing traffic conditions and efficiently implement high-level strategies at both local and city-wide scales".
 
The AI signal control system, which Vivacity says is the first of its kind, went live early this year and now simultaneously controls three neighbouring junctions in the Blackfriars area of Salford.

"Congestion and queuing can be reduced by traffic signals that respond better and more quickly to changes in traffic conditions than existing systems," the company adds.
 
This is part of a three-year Innovate UK co-funded programme to use AI to optimise traffic networks, and the UK government's 5G Create fund has been tapped for further cash to allow the project to scale up to 20 junctions in Manchester by the end of 2021.

Richard Dolphin,  TfGM highways network performance manager, says: “We’ve been really impressed with how Vivacity has approached this, assessing current ways of working and addressing the complexities of managing a multimodal transport network. Hopefully, this development will continue into something that will positively disrupt the industry and revolutionise active travel in urban areas.” 

For more information on companies in this article

Related Content

  • Data clears the road, says TomTom
    July 11, 2025
    Technology is one of the main tools in cutting congestion quickly and effectively. But it can’t just be about making things better for car drivers, explains TomTom’s Andy Marchant…
  • Huawei opens door to new opportunities in transport & logistics
    December 18, 2024
    By addressing the four key elements of a transportation network’s composition with a state-of-the-art digital solution, Huawei is bringing significant performance uplifts to all aspects of railway operations
  • Hard shoulder running aids uniform traffic flow and safer driving
    January 23, 2012
    David Crawford detects a market for European experience. Well-established now in at least three European countries, Hard Shoulder Running (HSR) on motorways is exciting growing interest in the US. A November 2010 Report to Congress by the Federal Highway Administration (FHWA), on the Efficient Use of Highway Capacity, notes the role of HSR in the European-style Active Traffic Management (ATM) strategies now being recommended for implementation in the US where, until recently, they were virtually unknown.
  • Getting connected with Wejo
    July 1, 2022
    New cloud-based platform allows researchers to run mobility studies using CV data