Google unveils table tennis pro robot 'Ping Pong'

AI-powered robot from Google DeepMind has amateur human-level performance in table tennis


Google’s DeepMind has revealed its new AI-powered robot that can compete and even beat any average table tennis player.

According to Futurism, the company made the announcement about its new robot on X (formerly Twitter), saying, “It is the first agent to achieve amateur human-level performance in this sport."

Google DeepMind further explained, “The robot has to be good at low-level skills, such as returning the ball, as well as high-level skills, like strategising and long-term planning to achieve a goal.”

Moreover, DeepMind in its official documentation wrote that table tennis ‘requires years of training for humans to master,’ adding, “(The sport is a) valuable benchmark for advancing robotic capabilities, including high-speed motion, real-time precise and strategic decision making, system design, and enabling direct competition with a human opponent.”

Scientists used AI algorithms to ‘adapt to various opponents by tracking their behaviours and playing style, such as which side of the table they tend to return the ball to.’

DeepMind also asserted, “Whilst the robot lost all matches vs. the most advanced players, it won 100 percent matches vs. beginners and 55 percent matches vs. intermediate players.”

To note, all the players who played against the ‘ping pong’ robot shared that their overall experience was engaging and everyone was interested in playing with a robot in the future.