Artificial active

Football advances artificial intelligence – here’s how

  • The complexity of football makes it a challenge for artificial intelligence and autonomous technologies.
  • The International RoboCup Federation organizes robot football matches and publishes scientific papers on machine learning.
  • Experts note that advances in robotic football have important implications for other forms of automation.

In 1997, a computer program named Deep Blue defeated the reigning world chess grandmaster, Garry Kasparov, in a highly publicized multi-day chess match. Enthusiasts debated the fairness of the game, but the computer’s victory was a major milestone for machine learning.

Today, researchers are using another game to advance artificial intelligence (AI) and automation: football.

The agility, strategy, and teamwork required in football make this beautiful game a challenging and fruitful feat for AI and autonomous technologies. The International RoboCup Federation, which organizes robotic soccer tournaments around the world, has long spearheaded such efforts.

“The RoboCup is a very special and inspiring event,” said Peter Stone, former RoboCup President and Executive Director of Sony AI America, an AI development and research company. “It merges ambitious, long-term thinking about how AI and robotics will change the world with practical, immediate considerations about how to design, build and program prototypes, bespoke robots to sense, decide and to act.”

Artificial Intelligence (AI) is impacting all aspects of society – homes, businesses, schools, and even public spaces. But as technology advances rapidly, multi-stakeholder collaboration is needed to maximize accountability, transparency, confidentiality, and fairness.

The World Economic Forum’s Platform for Shaping the Future of Technology Governance: Artificial Intelligence and Machine Learning brings together diverse perspectives to drive innovation and build trust.

  • Human resources is an area of ​​work well positioned to leverage AI, including hiring, talent retention, training, benefits, and employee satisfaction. The Forum has created a Human-Centered Artificial Intelligence Toolkit for Human Resources to promote positive and ethical use of human-centered AI for organizations, workers, and society.
  • Children and young people today are growing up in an increasingly digital age where technology permeates every aspect of their lives. From robotic toys and social media to the classroom and home, AI is a part of life. In developing AI Standards for Kids, the Forum is working with a range of stakeholders to create actionable guidelines to educate, empower and protect children and young people in the age of AI.
  • The potential dangers of AI could also impact society at large. To mitigate risk, the Forum brings together more than 100 businesses, governments, civil society organizations and academic institutions in the Global AI Action Alliance to accelerate the adoption of responsible AI in the global public interest.


  • AI is one of the most important technologies for businesses. To ensure that C-suite leaders understand its opportunities and risks, the Forum created the Empowering AI Leadership Toolkit: AI C-Suite Toolkit, which provides practical tools to help them understand the impact of about their roles and make informed decisions about AI strategy, projects and implementations. .
  • Shaping how AI is integrated into public sector procurement processes will help define best practices that can be applied across the private sector. The Forum has created a set of recommendations designed to encourage broad adoption, which will evolve with information from a series of trials.
  • The Center for the Fourth Industrial Revolution in Rwanda worked with the Ministry of Information, Communication Technology and Innovation to promote the adoption of new technologies in the country, stimulating policy innovation data and AI, especially in healthcare.

Contact us for more information on how to get involved.

According to the rules of the RoboCup, each team must consist of fully autonomous robot footballers; once the match has started, human coaches are not allowed to interact with their robot players. Stone, who is also a professor of computer science at the University of Texas at Austin in the United States and director of the university’s Learning Agents Research Group, noted that achievements in robotic soccer have advanced a range of areas of AI and machine learning. This includes human-robot interaction, computer vision, and multi-agent systems, among others.

These advances are shared in the RoboCup Symposium, a publishing arm of the organization that has so far produced hundreds of scientific papers detailing machine learning breakthroughs emerging from competitions.

RoboCup is a sustainable grand challenge for AI and robotics and a training ground for the next generation

—Peter Stone, professor of computer science at UT Austin, executive director of Sony AI America and former president of RoboCup

Football has also been used recently to advance AI by researchers who successfully created digital footballers who learned the game by competing against each other in a computer simulation. The project, published in August in Scientific roboticsa peer-reviewed scientific journal, used human movement data and other machine learning systems to enable players to perform and improve their soccer skills.

“We addressed the integration of motor control and long-term decision making in the context of simulated humanoid soccer, which requires agile motor control and multi-agent coordination,” the research team wrote. “Our work constitutes a comprehensive demonstration of integrated decision-making learned at multiple scales in a multi-agent environment.”


Experts note that advances in robotic football have important implications for other forms of AI and automation such as self-driving cars and care robots.

“In many countries, we have populations with insufficient numbers of young people to care for their elders. Robots will be the means by which this care can be delivered to keep people active and at home longer. Autonomous vehicles will bring mobility to older generations,” said Kay Firth-Butterfield, head of AI and machine learning at the World Economic Forum. “These important real-world applications can start with the creation of robot footballers where agility, machine vision and machine learning tests are essential to play the game.

RoboCup, for example, has expanded its efforts to include new competitive leagues that feature autonomous service robots. This includes the [email protected] league, which focuses on developing robotic personal and household service capabilities. The organization also hosts the RoboCup Rescue League where teams compete to develop advanced robotic tools for emergency responders. The most recent winner of this tournament was a research team from Kyoto University in Japan whose search and rescue robot showed new dexterity.

The inherent complexities of football continue to make the RoboCup Football Tournament a major source of inspiration and challenge for robotics and artificial intelligence researchers.

“Will football follow the path of chess, checkers, poker, Jeopardy, Starcraft, Gran Turismo and other hitherto human endeavors that have been conquered by AI? Or the demands of Will real-world perception and human speed and agility keep it out of reach?” Pierre asked. “This question remains a source of debate and uncertainty within the community.

Nevertheless, the organizers of the RoboCup maintain an ambitious goal: by the middle of the 21st century, a team of fully autonomous robot footballers will face the last winner of the World Cup and win.