Home / Blog / Testing self-driving cars in a smart cyberspace

Testing self-driving cars in a smart cyberspace

A Digital Twin of a self-driving car will be driving in the cyberspace powered by AI to face a variety of road situations and prove its reliability. Image Credit University of Warwick, UK

As part of its Future Mobility Grand Challenge – watch the clip- the UK Government is funding the creation of a sophisticated ambient simulator, OmniCAV,  recreating 32 km of Oxfordshire roads, including rural and village roads.

OmiCAV will be used as a testing environment for CAV -Connected Autonomous Vehicles- and it is based on an artificial intelligence engine that is trained on the actual traffic and events occurring on the road and that will be enacting them on the tested CAV.

For testing the CAV will be mimicked by its Digital Twin, the software that analyses the environmental data, as detected by sensors, create the CAV awareness and take decision. The OmniCAV can potentially accommodate an unlimited number of CAVs for testing and it can actually use the CAVs behaviour as a component of the testing environment so that one CAV is evaluated on its behaviour with respect to the AI generated situations and against the behaviour of other CAVs. I guess this will be useful to asses the interaction of CAVs, a crucial aspects that has gone mostly unnoticed so far. Autonomous vehicles are taught to make up their own mind based on their perception of the environment, which makes sense since they need to be autonomous and not rely on external guidance. At the same time the “training” is being made on today’s environment, so they learn how to react to today’s players (normal cars, bikes, pedestrians, dogs…) but not to other CAVs. The point is that we are going to have -likely- a variety of CAVs from different manufacturers, each with its own view of “reality” and its own way to respond to it.

Having the possibility to test their interaction is surely a plus.

The proposer of OmniCAV are expecting to turn a profit from offering testing services. They estimate a market for this testing of the order of 1,165 billion US$ by 2035 (66BUS$ in the UK) generating thousands of jobs worldwide (27,000 expected in the UK alone).

In perspective I can imagine much larger “test beds” based on the digital twins on cities and infrastructures. Next year, 2019, we are going to have the first digital twin of a city, Singapore, and several more will follow. Why not use these digital twins to host CAVs digital twins and test them?

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.