NW Tech Transformers Banner

Posted on April 5, 2018 by staff

A game-changer for driverless cars?

Simulation technology originally developed for computer gaming is now being used to accurately test and ‘train’ autonomous vehicles without using real roads.

Hertfordshire-based technology firm rFpro has launched what it claims to be the world’s first commercially-ready platform to train and develop driverless cars in a safe virtual world.

Two major car makers have already signed up to use the new platform, which uses a digital environment to accurately represent the real world and allows manufacturers to test their systems in every scenario imaginable.

Chris Hoyle, technical director at rFpro, believes that autonomous vehicles are the future but says they are “simply not ready to be used on our roads with guaranteed safety yet”.

“Autonomous vehicles are the future, the market is expected to be worth up to $10 trillion, but debate is rising about whether these vehicles should be allowed on our roads, if not, how do we develop them?” he said.

Hoyle argues that hardware such as cameras and sensors are already approaching the level needed to achieve a fully autonomous world – but the ‘brain’ needs to be further developed.

“Our platform allows  vehicle manufacturers to thoroughly test their technology and be absolutely confident in their systems before validation on real roads,” he said.

The technology has been developed over the last three years and has already been adopted by two vehicle manufacturers and three autonomous car developers.

It is also being used by a driverless motorsport series.

The digital platform gives users control of all the variables, such as traffic, pedestrians, weather and location, enabling them to test every eventuality.

It also allows humans to be introduced into the simulation, which Hoyle says is the best way to assess an autonomous vehicle’s decision making.

It is estimated the new platform will allow vehicle manufacturers to carry out the equivalent of two million miles of testing every month, which will speed up the development of driverless cars and significantly reduce the cost and time needed.

“By using multiple computers 24/7, manufacturers can undertake millions of miles of testing every month using our platform,” said Hoyle.

“Humans can also be introduced into the simulation, controlling surrounding cars or pedestrians, so we can assess an autonomous vehicle’s decision making and also the interaction between the vehicle and the driver, but most importantly it is carried out in a safe environment.”