City Science
City Science
City Science
City Science

“We needed a unique skill set to help develop our tools. The Impact Lab team was amazing - easy to work with and delivered excellent quality ouputs, on time. I definitely recommend working with them.”

Laurence Oakes-AshCEO, City Science

The Project

In this award-winning project, the Impact Lab is working with City Science to use autonomous vehicles to solve the difficult ‘Last Mile Problem’ of getting travellers to and from transport hubs, such as train stations.

One of the primary deterrents for people taking a form of public transport (e.g. train) is the problem of getting from home to a station and then getting to their final destination once they get off the train, due to poor local public transport coverage or mobility issues. While some passengers are fit enough to solve their last mile problem by hopping on a bicycle, other less physically able consumers are excluded from affordable last mile connections, not to mention the rise in traffic during adverse weather conditions, and the danger to cyclists with no cycle paths available on their route.

We are not far away from a future where these kinds of problems can be addressed using self-driving vehicles, with ‘connected and autonomous vehicles’ (known as CAVs) able to ferry people on short journeys quickly, safely and affordably. City Science is enabling this future by building a data-driven strategy for bringing CAVs into our transport systems. One of the essential questions to answer to make a CAV solution effective and affordable for local authorities, is to optimise the distribution of the vehicles to maximise the convenience to users and encourage more people to switch from their cars to public transport.

The Approach

Bringing their Last Mile project to the Impact Lab for support has allowed City Science to access the skills of our Machine Learning specialists, who are experts in solving optimisation challenges. By combining the subject matter expertise and data sets gathered by the team at City Science, with this machine learning capability, City Science has been able to build a more robust and reusable optimisation system.

The Results

The optimisation software under development will make the Last Mile CAV solution a more commercially viable service that urban planners and transport authorities can deploy to reduce congestion in cities across the UK and around the world.

You can view and download the winning report here.

The Team

City Science:

  • Laurence Oakes-Ash, CEO & Co-Founder, City Science
  • Rob Byrne, Chief Technical Officer, City Science
  • Alex Dawn, Transport Consultant, City Science

Impact Lab:

  • Kathryn White, Innovation Manager, University of Exeter
  • Dr Alma Rahat, Industrial Research Fellow, University of Exeter
  • Dr Ralph Ledbetter, Industrial Research Fellow, University of Exeter