Sony’s Gran Turismo AI racer can drift now, making it even more unbeatable

Sony’s Gran Turismo AI racer can drift now, making it even more unbeatable

The world’s leading Gran Turismo 7 players have had their shot at beating Sony’s AI racer, GT Sophy, and they lost spectacularly. Now, the bot has added drifting to its move set to rub salt on the wounds, as seen in a video from the Gran Turismo World Series 2023 event. The video clearly shows an AI-controlled vehicle drifting around the track like an absolute maniac. Meanwhile, most people can’t pull off successful drifts in Mario Kart, let alone in realistic racers like Gran Turismo.

GT Sophy, you can guess what the GT stands for, is the result of more than six years of development between Sony AI and Sony Interactive Entertainment, and utilizes deep reinforcement learning methods. These methods have trained the artificial intelligence algorithm to control the digital race car within the game’s structure and limitations. When first unveiled, Sophy was a master at various racing tactics like slipstreaming, passing and blocking, though drifting is a new move for the bot.

Sony says that GT Sophy is here to stay, stating that the company’s continuing its efforts to make the AI a “permanent part of the game.” To that end, Sony let regular Gran Turismo 7 players face off against GT Sophy last year for a limited time, so maybe that promotion will return.

For the uninitiated, drifting is a popular move in both real-world racing and its digital equivalent. First introduced in the 1980s by Japanese racer Keiichi Tsuchiya, drifting involves steering a vehicle so it makes a controlled skid sideways through a turn. This allows you to quickly take steep turns, shaving off crucial seconds from a run.

See also  Cyber threats spur brokerages to seek tech partners

Now that algorithms can perform this feat, don’t count on outracing any evil robots when the AI apocalypse starts. You should probably just hide instead, or ply Alexa with compliments to get on her good side.

Related video: