‘Deepfake’ Tech To Help Autonomous Driving Research

Thu 25th Jun 2020

A team of software developers from Oxford University are using the tricks of viral videos on the internet to help speed up the development of autonomous vehicles.

‘Deepfake’ videos employ sophisticated artificial intelligence to help create fake internet videos whereby faces and scenarios in famous movie scenes can be substituted. The technology is now being used by Oxbotica, a start-up founded by Oxford graduates to help generate millions of images which can ‘expose its autonomous vehicles to the near-infinite variations of the same situation’. One example might be to show the same section of road, but with a variety of different weather conditions such as rain, fog, or different light conditions.

The aim is to create real-life experiences for autonomous driving technology without the need to go out on the road to recreate ‘real-world’ scenarios.

“There is no substitute for real-world testing”, said Oxbotica co-founder Paul Newman, “but the autonomous vehicle industry has become concerned with the number of miles travelled as a synonym for safety… You cannot guarantee the vehicle will confront every eventuality. You’re relying on chance encounter. The use of deepfakes enables us to test countless scenarios, which will not only enable us to scale our real-world testing exponentially, it’ll also be safer.”

The technology can make changes to road signage, layouts and even replace objects with a high level of accuracy, it’s hoped that the software will allow the AI to teach itself the millions of different scenarios a driver may encounter on a car journey.