Autonomous vehicles learn from GTA V

The blockbuster video game by Rockstar Games is among simulators training auto-piloting software.

Scientists from the Darmstadt University of Technology in Germany and Intel Labs have developed a way to pull visual information from Grand Theft Auto V. Thanks to that, other researchers derived algorithms from its software that’s been tweaked for use in the self-driving sector.

GTA V‘s features are pretty close to reality, with 262 types of vehicles; more than 1,000 different (and unpredictable) pedestrians and animals; 14 weather conditions; and countless bridges, traffic signals, tunnels, and intersections.

According to Davide Bachet -from startup Nio whose team aims to introduce an autonomous electric car in the U.S. in 2020-, “just relying on data from the roads is not practical” and “with simulation, you can run the same scenario over and over again for infinite times, then test it again.”




No responses

Add comment