Ace, an autonomous robot powered by AI, cutting-edge sensors and an extremely dexterous arm with eight joints, has played competition-rule table tennis and beaten elite human competitors. The robot is the first machine to excel at the sport.

It was the cerebral game of chess that was first disrupted by computers, but Ace’s success suggests physical sports may be about to have their “Deep Blue” moment – the day, in 1997, that a machine of that name beat world chess champion Garry Kasparov.

“Games have long served as benchmarks for AI, including chess for Deep Blue, but also other games in more recent breakthroughs, like [the Go-playing AI] AlphaGo,” says at Sony AI, Zurich Switzerland, who led the team that built Ace.

But he says those earlier AI milestones were played out online. Ace represents an important advance because it has taken on real-world, professional table tennis champions and held its own.

“Ace offers something that has simply never been captured before: a robot and a human in genuine athletic competition,” says DĂŒrr.

Ace boasts three main advancements in autonomous robotics, he says. Firstly, it uses “event-based sensors”, which means that the robot focuses on certain regions of the images its cameras capture – those indicating changes in motion or brightness, which are critical to tracking the path of the table tennis ball.

Free newsletter

Sign up to The Weekly

Sign up to newsletter

Next, the robot’s table tennis skills are built using “model-free reinforcement learning”, which means, says DĂŒrr, the robot “learns through experience in simulation rather than adopting a model of how table tennis should be played”. This process was similar to having the robot play a table tennis computer game, and the robot notched up several thousand hours of training during the process.

And finally, the team has deployed high-speed robot hardware that allows Ace to play with “human-like agility”, says DĂŒrr. In some ways, it is even more agile than a human, because athletes require around 230 milliseconds to react, he says, whereas the total latency of Ace is only around 20 milliseconds.

Currently, the robot looks like a robot from a factory floor, and relies on a network of cameras and sensors surrounding the table tennis arena. But as the technology advances, the researchers expect Ace will eventually be embodied in a humanoid form.

For the matches played as part of a study published today, Japanese professional table tennis league rules applied as Ace competed against five elite but non-professional players, each of whom had competed for at least a decade and trained 20 hours per week. The robot also took on two professionals.

Ace lost only two of its five matches against elite players, but both of its matches against professional players. It did, however, achieve a win in one game within one of the professional matches.

Another advantage that Ace has over humans is that it does not give away any tells of its next move. On the other hand, it lacks the capacity to read any signs of the body language of humans.

“Some of the athletes involved in our experiments commented that they are usually watching their opponent’s face – which Ace does not have,” says DĂŒrr.

Others were surprised by Ace’s ability to read the spin of their serves, despite their attempts to hide it with different motions. The robot also confounded its inventors – especially when it was able to hit balls that bounced off the net, which was not a skill it had trained for. This was a skill that just “emerged”, says DĂŒrr.

Over the past year, since the study was completed, the team has continued to improve Ace’s abilities.

The moment that kicked off the AI revolution

It's been 10 years since Go champion Lee Sedol lost to DeepMind's AlphaGo. Has the technology lived up to its potential?

In December 2025, Ace beat a professional player for the first time, and in March 2026, Ace won matches against three more professional players: a female professional, , who is ranked in the top 25 in the World Table Tennis ranking, as well as two male professionals, and .

“With further improvements, it should be possible to outperform even the world champion,” says DĂŒrr.

And improvements go both ways, he says.

“Former Olympian noted that before watching Ace, he thought a certain shot was impossible, but having seen it, he believes human athletes could replicate this technique.”

The idea that we should make lifestyle adjustments depending on where we are in our menstrual cycle is gaining traction online, as well as in scientific circles. Now, researchers have found that athletes who obtain a sports injury while on their period seem to take longer to recover from it than at other times in their cycle.

#cyclesyncing is tagged in thousands of social media posts that promote altering diet and physical activity levels around the different stages of the menstrual cycle, to adjust for the hormonal changes that occur. The evidence supporting such dietary changes is weak, and while exercise-related studies on this subject are more robust, their results have also been mixed. Nevertheless, rugby union teams in the US and England already .

To try to better understand this, and her colleagues at Hospital Sant Joan de DĂ©u in Barcelona followed 33 professional football players from the FC Barcelona women’s team across four seasons between 2019 and 2023.

As part of their normal training regimen, the women self-reported the days when they were on their period. Any injuries that occurred over the seasons were categorised in terms of severity by a doctor using a standard scale.

The researchers found that although the women didn’t obtain more injuries while they were on their period, the ones they did get during this time appeared to be more severe. For instance, soft tissue injuries sustained during this time resulted in more than three times the number of days of training lost compared with when such injuries occurred at other times.

This may be because oestrogen levels are low during a period. . “The combination of low estrogen, possible iron loss, more intense symptoms [such as cramps] and greater fatigue could contribute to a worse prognosis for injuries at this stage,” says Ferrer.

Free newsletter

Sign up to Health Check

Sign up to newsletter

However, at McMaster University in Canada points out that we don’t fully understand oestrogen’s role in muscle repair. “The ethos is that estrogen is protective and reparative [for muscles], but the majority of that comes from animal studies and not human trials,” he says. The study also didn’t measure the women’s iron levels or potential confounding factors, such as fatigue.

Ferrer accepts that few injuries occurred overall, with 69 taking place on non-bleeding days and just 11 while bleeding. “A small number of very serious injuries can skew the overall impression if the sample size and confidence intervals are not taken into account,” she says. We also don’t know whether the results apply to those who exercise or do sport more casually, rather than at a professional level, says Ferrer.

Periods are starting younger and we’re struggling to pin down why

Menstruation is occurring earlier and earlier in life for younger generations in the Western world, but researchers are puzzled as to why

She hopes the picture will become clearer with further research, which could lead to bespoke exercise recommendations at different times in the cycle. “The most responsible approach is that decisions regarding training load and type during menstruation should be individualised,” says Ferrer, “taking into account each player’s symptoms and relying on objective data (internal and external load, injury history, well-being, etc.), while research continues to incorporate hormonal measurements, iron markers, sleep patterns, nutrition and other variables that can help refine recommendations.”