20 hours ago
How Artificial Intelligence is helping badminton players improve their games
There is an epidemic of poorly executed forehand air tosses in badminton, amongst the hundreds of player videos collated in Bengaluru. A bug was blighting the feature.
An AI-powered review system had picked up the trend pointing to the weakness of that high altitude shot amongst upcoming shuttlers, mostly beginners. It has zeroed in on the elbow not being properly stretched and the balance being slightly off, suggesting foot placement and arm control drills to a specific shuttler. All that the shuttler had done was upload a video of a training session/match, and the VisistAI tech from a Bengaluru startup, reeled off a basic analysis of the toss – one of the tactical weapons deployed in matches that demands consistency and accuracy on the time of contact of shuttle with racquet.
The tech startup is attempting to fill up a gap for grassroots badminton players by offering them access to biomechanic tools that analyse their technique and suggest corrections. 'One insight that was massive from the VisistAI review was that several players had a weak forehand toss, and were scoring less from that shot. It was an instruction to coaches to work with strength & conditioning coaches. Our tools provide elite insights at various stages of play by assessing skill, strokes and agility,' says Suresh Chintada, co-founder and CEO of VisistAI.
Players record their games on a smartphone mounted on a tripod, and send it off for AI model to threadbare their techniques. Typically, a rudimentary report throws up reviews on assorted skills like grip, the forehand keep shot, backhand serves besides the toss. 'Besides agility, we can track specific postures, movements on court, and shuttle flights,' explains Seshadri Raghavan, co-founder and chief tech officer.
Almost 70+ Bengaluru academies are availing of this service, ensuring a single coach can actually keep track of several games. 'We have assessment reports and smart journals that we send to the coaches, and AI acts like an assistant coach,' Suresh says.
Searchable bookmarked footage with dashboards showing historical trends and improvements tracked over several weeks, is available even as the AI assessment uses Rubric templates (predefined parameters in boxes), and reports are available in local languages.
An almost imperceptible smashing technique tweak once came up when the AI model noted, 'Preparation of elbow and arm is too low before smashing. In under pressure situations it is difficult to get good angles on the smash.'
A simple grip – though all-important- is assessed for consistent relaxed hold, finger placement, follow through of wrist, while pointing out that tiny foot shifts tend to disturb execution. 'Improve explosiveness to reach the shuttle sooner. Work on smoother timing on serves and reinforce elbow alignment in air toss,' It summarises. Grip relaxing exercises on the odd occasion it gets too tight and impedes a stroke, are advised.
For a particular shuttler, the AI model pulled out Frame No 376 for ideal shot placement on a forehand keep shot, while shuttle placement is a weakness. On the backhand serve, the player was advised steadying the stance even if it's only in a couple of instances.
'For an experienced coach, the AI model is an augmented, unblinking view with a couple of dimensions added to look at movement, posture,' says Suresh who adds that coaches have returned to tell him their level of coaching and numbers of competitive players has gone up with access to this information which is now objectively and democratically available – though at a price.
The duo always fancied sports – tennis and even running technique of marathons, though VisistAI is available for similar analyses in cricket and basketball. But all AI developments need to be taken with a pinch of salt, and the duo insist no AI can replace a coach. 'AI will never replace a coach. It's not in a position to understand mental aspects like a 'bad day' which can have a massive impact on the game. But now anybody can become a coach and access this,' Suresh adds.
Access to elite coaching is 0.1 percent in India and 25 percent in the USA, and AI models with workflow charts can help bridge these gaps.
The startup hopes to add human expert coaches to the panel to go a step further in making advice available. But the ambitions ultimately extend to predictive analysis, and the final frontier is stopping injuries from happening. 'Injury prevention is the goal. Right now tech is used in biomechanics and rehab level. But if we can predict injury before it happens and reduce chronic stress ..' says Seshadri.
