This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:


peer-reviewed publication

trusted source


Tiny AI-trained robots demonstrate remarkable soccer skills

Tiny AI trained robots demonstrate remarkable soccer skills
The robot soccer environment. Credit: Tuomas Haarnoja

A team of AI specialists at Google's DeepMind has used machine learning to teach tiny robots to play soccer. They describe the process for developing the robots in Science Robotics.

As machine-learning-based LLMs make their way into the , continue to look for other applications for AI tools. One purpose that has long captured the imagination of scientists and the public at large is the implementation of robots that can carry out traditionally human tasks that are difficult or arduous.

The basic design for most such robots has typically involved using a direct programming or mimicking approach. In this new effort, the research team in the U.K. has applied machine learning to the process and has created (approximately 510 mm tall) that are remarkably good at playing .

Humanoid robots, trained to play soccer with deep reinforcement learning, play a one-versus-one soccer game. Credit: Google DeepMind

The process of creating the robots involved developing and training two main reinforcement learning skills in —getting up off the ground after falling, for example, or attempting to kick a goal. They then trained the system to play a full, one-on-one version of soccer by training it with a massive amount of video and other data.

Once the could play as desired, the system was transferred to several Robotis OP3 robots. The team also added software that allowed the robots to learn and improve as they first tested out individual skills and then when they were placed on a small soccer field and asked to play a match against one another.

Side-by-side comparison of learned versus scripted behaviors. Credit: Tuomas Haarnoja

In watching their robots play, the research team noted that many of the moves they made were accomplished more smoothly than robots trained using standard techniques. They could get up off the pitch much faster and more elegantly, for example.

The robots also learned to use techniques such as faking a turn to push their opponent into overcompensating, giving them a path toward the goal area. The researchers claim that their AI robots played considerably better than robots trained with any other technique to date.

More information: Tuomas Haarnoja et al, Learning agile soccer skills for a bipedal robot with deep reinforcement learning, Science Robotics (2024). DOI: 10.1126/scirobotics.adi8022

Journal information: Science Robotics

© 2024 Science X Network

Citation: Tiny AI-trained robots demonstrate remarkable soccer skills (2024, April 11) retrieved 28 May 2024 from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

A model that could broaden the manipulation skills of four-legged robots


Feedback to editors