UK researchers are working on a project aimed at enabling autonomous vehicles to learn to ‘swarm’ together like insects.
According to one of the research partners, automotive industry supplier RDM Group, the concept is based on “fusing together” existing information from other autonomous vehicles in a fleet of pods to allow each pod to locally decide the most appropriate action for the group as a whole – similar to how insects and birds behave.
This means that pods can highlight any unexpected behaviour to a supervisor, as well as giving local authorities the chance to take advantage of ‘platooning’, where vehicles follow each other when possible to minimise the number or individual vehicle movements.
The technology also enables the system to automatically adapt its behaviour to meet demand so that pods can be optimally distributed within a city to the areas where they are most likely to be requested.
“Significant time and investment has been channelled into developing on-vehicle driverless technology” commented Simon Brewerton, Chief Technology officer at RDM Group.
“However, for the economic, social and environmental benefits to be truly realised, traditional swarming approaches developed in the fields of Artificial Intelligence and computer science need to be applied to fleets of autonomous vehicles so that they can function collectively and with maximum efficiency.”
The SWARM project, funded by the UK Government’s innovation agency, Innovate UK, also involves the University of Warwick’s WMG (Warwick Manufacturing Group) and Milton Keynes Council.
Brian Matthews, Head of Transport Innovation at Milton Keynes Council, said that the project will demonstrate the application of this technology in a real urban environment.
“We will be demonstrating the service within Milton Keynes, on open footways shared with other users. Our aim is to show how a viable last mile transport service can support a transformation in how we move around cities, opening affordable sustainable mobility for all.”
Dr Stewart Birrell, Assistant Professor at WMG, added: “Research and development is moving away from the technical challenges of making these autonomous pods self-driving towards how a fleet of pods will be deployed in the ‘real-world’.”
