Networked Intelligence makes cars safer

Networked intelligent vehicles. Credit: EPFL

Work is accelerating on increasing the autonomy of cars, aiming at self driving cars in the next decade, and in their cooperation to increase safety.

This latter goal, although self evident, is much more complex that it would seem. Imagine two cars, one following the other. It is evident that the first one might spot an obstacle, like a pedestrian “before” the one following and could inform the latter of the incoming, potential, danger. Yet, if the localisation systems of the two cars are not synchronised the car following might also spot the pedestrian by t

he time it receives the information from the preceding car but its localisation system may place it at a distance of 50cm from the one identified by the preceding car, hence the assumption that there are two pedestrians, not one.

It is a simple example just to point out the crucial role played by a common perception of the environment.

This aspect is being studied at EPFL, in Switzerland, where they look at creating an overall cooperative perception to make cars smarter.

They are experimenting with two Citroen C-Zero electric cars retrofitted with a MobileEye camera for accurate localisation and a WiFi router. Their intelligent algorithm evaluates the potential risk of passing, gauging the probability of an incoming vehicle, or obstacle, taking into account the speed of the two cars and the one of the incoming obstacle.

Although they are now testing their software on two vehicles the longer term goal is to create a collective perception across many cars moving in the same area.

Interesting also their approach based on retrofitting existing cars.  It is likely that retrofitting, particularly for safety reason, may become a multi billion business, given the life cycle of vehicles. Today’s vehicles have the electronics that can support this kind of retrofitting and in the next decade most of today’s cars will still be on the road. The new generation will be equipped with the advanced driving assistant features and it will greatly improve the overall safety if we can retrofit existing vehicles.

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.