Fans at the Olympics are testing a new AI-powered system designed to identify future gold medallists. The developers plan to use a portable version to bring advanced sports science to remote regions worldwide.
When the alarm sounds, Tacto frantically swipes the infra-red sensors as they flash blue, while his younger brother, Tomo, sprints down a short track monitored by cameras. The seven and four-year-old siblings from Yokohama, Japan, are participating in AI-driven tests near the Paris Olympic Stadium.
The system aims to spot potential gold medallists by collecting data from five tests, including running, jumping, and grip strength.
“We use computer vision and historical data, so people can see which sport suits them best,” says Sarah Vickers, head of Intel’s Olympic and Paralympic Programme. After completing the tests, participants are informed of the sport they are most suited to, and all data is deleted once the process is done. Tacto enjoyed the experience, especially the sprinting.
The AI system at Paris 2024 has a portable version that can run on devices with basic cameras, enabling access to remote areas. Recently, the International Olympic Committee used the system in Senegal, assessing over 1,000 children for athletic potential. After further tests, 48 children with “significant potential” and one with “exceptional potential” were identified and offered places in sports programmes.
Professor John Brewer from the University of Suffolk acknowledges the system’s potential but cautions that it may be limited in technical or endurance sports. He sees value in initial assessments but stresses that it should be part of a broader talent identification process.
Tacto, thrilled with his results, was identified as a potential sprinter, although he currently prefers football and tennis.