TacticAI: Google DeepMind Pioneer a Sports-Led AI Assistant

Google DeepMind’s TacticAI has been launched as part of a research collaboration with Liverpool FC to transform the sporting experience with AI

Launched by Google DeepMind, TacticAI holds potential to revolutionise sports analysis with the power of AI.

As part of a multi-year collaboration with Liverpool FC, the AI tool is designed to provide football coaches with player insights. These can range from suggesting player positions to predicting who can receive the ball. Google DeepMind has found in its research that the AI proposals were preferred by human expert raters 90% of the time, as opposed to human-led tactical setups.

TacticAI could allow coaches to spend less time manually reviewing videos and more time devising successful strategies.

Using deep learning to improve sports performance

This is not the first time that machine learning has become involved in football. Last year, ABBYY partnered with Arsenal Women’s Football Club to offer a range of AI solutions, including streamlining tasks and improving efficiencies.

More generally, the sports world is starting to use AI more frequently to assist game coverage and improve spectator experience. Wimbledon in particular adopted AI-powered commentary in a significant milestone that combined advanced technology with traditional sports coverage. Such transparency ensured that viewers were aware of when human commentators were speaking or when AI algorithms provided insights.

When it comes to TacticAI, the model incorporates both a predictive and generative component. This enables football coaches to test different tactics and explore alternative player setups, selecting those with the highest predicted likelihood of success.

Working in collaborating with Liverpool FC enables the AI to analyse different football kicks and offer coaches direct opportunities for interventions and improvements. TacticAI has been validated on a number of benchmark tasks, including predicting receivers, shot attempts and recommending player position adjustments.

TacticAI can demonstrate how assistive AI techniques can work to revolutionise sports for players, coaches and fans alike. Google DeepMind highlights in its announcement: “Sports like football are a dynamic domain for developing AI, as they feature real-world, multi-agent interactions, with multimodal data. 

“Advancing AI for sports could translate into many areas on and off the field – from computer games and robotics, to traffic coordination.”

Google DeepMind: Advancing society with the power of AI

The company has sought to revolutionise multiple key industries with its AI progress, including its launch of GNoME at the end of 2023 to discover and develop new materials at scale.

It was also instrumental in launching Google’s Gemma AI model, which has been built for responsible AI development to suit a wide range of business use cases.

Through TacticAI, Google DeepMind believes that it has achieved a milestone in useful assistants in sports AI. It hopes that future research in this area can contribute to expanding more multimodal inputs outside of player data and find other use cases to help experts.

“We show how AI can be used in football, but football can also teach us a lot about AI,” the company says. “With TacticAI, we hope to take many lessons in developing broader assistive technologies that blend human expertise and AI analysis to help people in the real world.”

************

Make sure you check out the latest edition of AI Magazine and also sign up to our global conference series - Tech & AI LIVE 2024

************

AI Magazine is a BizClik brand

Share

Featured Articles

AI and Broadcasting: BBC Commits to Transforming Education

The global broadcaster seeks to use AI to make its education offerings personalised and interactive to encourage young people to engage with the company

Why Businesses are Building AI Strategy on Amazon Bedrock

AWS partners such as Accenture, Delta Air Lines, Intuit, Salesforce, Siemens, Toyota & United Airlines are using Amazon Bedrock to build and deploy Gen AI

Pick N Pay’s Leon Van Niekerk: Evaluating Enterprise AI

We spoke with Pick N Pay Head of Testing Leon Van Niekerk at OpenText World Europe 2024 about its partnership with OpenText and how it plans to use AI

AI Agenda at Paris 2024: Revolutionising the Olympic Games

AI Strategy

Who is Gurdeep Singh Pall? Qualtrics’ AI Strategy President

Technology

Should Tech Leaders be Concerned About the Power of AI?

Technology