- Google DeepMind unveiled a prototype AI soccer tactics tool last month.
- TacticAI suggests corner kick strategies based on analysis of over 7,000 set pieces.
- DeepMind developed the tool with Liverpool FC, known for their data-driven approach to football.
Google DeepMind is bringing artificial intelligence (AI) to soccer by launching new tools to help coaches make better tactical decisions.
The London-based institute unveiled a prototype of TacticAI in March, developed as part of a three-year collaboration with English Premier League soccer club Liverpool FC.
DeepMind researchers published their findings in the scientific journal Nature Communications.
Soccer experts involved in the project say the AI system, trained on a data set of more than 7,000 corner kicks from EPL matches, is already better than humans at planning attacking and defending set-pieces. I believe there is.
“What’s the most fun? [soccer] Zhe Wang, one of the leaders of Google DeepMind’s TacticAI project, told Business Insider. “There’s a lot of randomness in games, but you can still use data to make better decisions.”
corner kick
Some of the most iconic goals in soccer’s recent history came from corner kicks.
In the 2012 Champions League final, former Ivorian star Didier Drogba scored Chelsea’s last equalizer from a corner with a memorable header, while Liverpool fans were impressed by Divock Origi’s ‘quick goal from a corner’. FC Barcelona was eliminated from the competition. In 2019, it became the club’s biggest goal in history.
Petar Veličković, co-author of the DeepMind project, told BI that it makes sense to train TacticAI because data taken from corners tends to lead to more structured passages of play. .
Soccer is “very unpredictable,” he says. “You can never predict exactly what will happen. But what you can do is notice patterns in tactics. Corners are very effective because they are strict, frequent, and lead to scoring chances. .”
TacticAI can make suggestions to coaches about the optimal positioning of players when attacking or defending corners, potentially giving teams small gains that tend to make a big difference in competitive sports.
Liverpool collaboration
DeepMind developed TacticAI in collaboration with Liverpool, earning praise from legendary Moneyball baseball executive Billy Beane.
Since being taken over by Boston Red Sox owner Fenway Sports Group in 2010, the club has hired several people with resumes not normally seen in EPL boardrooms. Among them is Ian Graham, who holds a PhD in physics from the University of Cambridge and is chairman. Liverpool’s research department until 2023.
Velickovic said having that knowledge at hand helped the collaboration between DeepMind and Liverpool go smoothly.
“For the past 10 years or so, Liverpool has had a team of people with PhDs from Cambridge and Harvard who are very engineering-, data- and research-oriented, and who use statistical analysis to work on their research. “For a long time,” he said. “So there was already a good, solid foundation on which deep learning could be built.”
Liverpool’s experts helped DeepMind determine whether TacticAI’s corner routines were effective, while both organizations worked extensively on the role of AI in soccer and systems that predict players’ off-camera movements in recent years. collaborated to create the study.
AI and soccer
The release of TacticAI marks the end of the partnership between DeepMind and Liverpool. But researchers believe top-level club executives are only just beginning to realize that AI could play a transformative role in football.
As well as corners, other set-piece events, including free-kicks, throw-ins and penalties, also provide the kind of structured data that AI tends to thrive on, and are what researchers in the field are looking at next. could become a field, they said. .
While some purists worry that such technological intervention will one day take some of the joy out of so-called “beautiful games,” researchers say they are He emphasized that he is trying to create tools that make coaches’ lives easier, not tools that make coaches’ lives easier. kick them out of their jobs.
“We are not trying to replace human coaches. Instead, through AI we help them recognize patterns and find opportunities for improvement so they can make faster and better decisions. We want to help them do so,” Wang said.
“Ultimately, it’s still the coach who makes the decision,” he added. “This is just a tool to support more comprehensive decision-making.”
On February 28, Axel Springer, the parent company of Business Insider, joined 31 other media groups in filing a $2.3 billion lawsuit against Google in Dutch court, alleging losses caused by the company’s advertising practices. I woke you up.
