I got training tips from an AI fitness coach and it feels like the future of athletic performance technology
Standing in the corner of a packed conference center in Barcelona, ββI probably looked a little unusual. As other smartly dressed MWC 2024 attendees shuffled past me, otherwise chatting amiably, hiding in their phones, or ogling the latest technology, I got at least a few strange looks. That was because I was sprinting on the spot and sprinting hard, trying to pull my knees higher each time, despite the fact that I was dressed in jeans and flat-soled vans.
In front of me was a camera, linked to a mirror-length smart display that guided me through a few simple training exercises. I had to run on the spot, jump back and forth and perform a single squat jump. There was also an Xbox Kinect-style cognitive reaction game, played on the smart display’s touchscreen.
Behind the scenes, artificial intelligence analyzed my performance and when the trial ended, it provided me with the kind of information you’d expect on the best Garmin watches: measuring my explosive strength, speed, coordination, agility and other metrics, all in simple scores of 100.
This was one of the more fun interactive displays I got involved with at MWC, but behind the sprinting, jumping, and bubble popping was a lot of cutting-edge technology that could have major implications in the fitness tech scene. ai.io has developed 3D Athlete Tracking, or 3DAT, which uses artificial intelligence and YOLO (βyou look onceβ) object detection for ‘human tracking’, identifying key points of the body and providing motion-based biometrics .
It is currently being used for footballers: a British app called aiScout allows young amateur players to record their training exercises and connects them with coaches. The coaches can then use these AI-generated metrics to identify promising young prospects.
However, football is far from the only use case: conversations with ai.io representatives and engineers revealed that discussions were underway with organizations such as the NFL, and that disciplines such as running were ‘on the roadmap’. This is great news for me: as an avid runner, I can only imagine the possibilities. Would you like to give yourself a running analysis to improve your running behavior at home or in the nearest gym with a treadmill, instead of making an appointment at a specialized running store to select the best running shoe for your running style? Sign me up.
My only question would be how reliable these statistics are: no two bodies are the same, and sometimes it takes a human mind to distinguish certain features. But you could say the same about smartwatches: I fight several times a week to bump up Garmin’s Endurance Score, which uses my VO2 Max data and Garmin’s algorithms to give me a single number that tells me how I’m doing. go. This is just an evolution of that methodology, using a single camera and some software instead of an expensive piece of hardware.
I’m curious to see where 3DAT goes, as just one example of athletic performance tracking using AI. If the technology only gets better, it will certainly do what AI seems to do best: disrupt. I predict that in the not-too-distant future we’ll see many more personal trainers, professional coaches and fitness enthusiasts pulling out their cameras instead of relying on power meters, heart rate monitors and even the best smartwatches.