While you might be playing GTA to remorselessly run over people for fun, researchers are now using the popular game to train computers how to better navigate self-driving cars in the real world.
Scientists from Darmstadt University in Germany and Intel Labs have developed a new clever method to source visual data from Grand Theft Auto that could then be fed to computers to teach vehicles how to drive autonomously.
Have you visited TNW's hype-free blockchain and cryptocurrency news site yet?
It's called Hard Fork.
Although machine learning is enabling computers to quickly pick up new skills, the approach requires large quantities of information to work effectively – and data could be hard to find sometimes.
It takes thousands of hours of real-world visual data in various scenarios to teach cars how to navigate on their own, but the researchers say information from games is easy to collect and can be “almost as good, or sometimes even better” than real data.
This is where Grand Theft Auto’s incredibly realistic environment comes in play.
The scientists created a software that is capable of classifying different objects on roads within the game. The data generated can then be used to teach self-driving cars the difference between pedestrians and other objects when navigating through the real world.
You can watch the video in the section above to see how the researchers are gathering data from Grand Theft Auto.
And while scientists are still figuring out the best ways to teach computers how to drive, companies from the likes of Google, Uber, BMW and Nvidia are in a heated race to conquer the nascent market of self-driving cars.