The robot already knows how to dribble, pass people, and score goals

Scientists at Google DeepMind trained the Robotis OP3 robot to play soccer using an AI training technique called deep reinforcement learning.

Scientists at Google DeepMind trained the Robotis OP3 robot to play soccer using an AI training technique called "deep reinforcement learning."

This machine learning training technique is the result of combining many different AI training methods. The algorithm works like artificial neurons, and is arranged to resemble the human brain.

Compared to robots not trained with AI, robots trained with this technique move 181% faster, turn 302% faster, kick a ball 34% faster and take 63% less time to recover. after falling during simulated matches.

The robot already knows how to dribble, pass people, and score goals Picture 1 The robot already knows how to dribble, pass people, and score goals Picture 1

From the video provided by scientists, it can be seen that the robot, after being trained with AI, can perform complex movements such as dribbling, blocking, passing people, scoring goals. in a relatively simple way. skillfully and at high speed.

The researchers added that the robot has developed emergency movement behaviors that are extremely difficult to program in soccer, such as spinning around to deceive the opponent, turning the angle of the foot.

The findings suggest that this AI training technique could help general humanoid robots produce simple, but relatively safe, movements. From there, the robot can be enhanced with more complex movements, and be applied more in life situations.

Similar technology was applied and successfully enabled the robot to make its own coffee after a training period of only 10 hours.