![](\"https:\/\/fortune.com\/img-assets\/wp-content\/uploads\/2026\/04\/AP26111743057206-e1776888979324.jpg?w=2048\")
<\/p>\n<\/p>\n
A paddle-wielding robot is so adept at playing table tennis that it is posing a tough challenge to\u00a0elite human players\u00a0and sometimes defeating them, according to a new study that shows how advances in\u00a0artificial intelligence\u00a0are making robots more agile.<\/p>\n
Japanese electronics giant Sony built the robotic arm it calls Ace and pitted it against professional athletes. Ace proved a worthy adversary, though one with some non-human attributes: nine camera eyes positioned around the court and an uncanny ability to follow the ball\u2019s logo to measure its spin.<\/p>\n
The robot learned how to play the sport using the AI method known as reinforcement learning.<\/p>\n
\u201cThere\u2019s no way to program a robot by hand to play table tennis. You have to learn how to play from experience,\u201d said Sony AI researcher Peter D\u00fcrr, co-author of the study published Wednesday in the science journal Nature.<\/p>\n
To conduct the experiments, Sony built an Olympic-sized table tennis court at its headquarters in Tokyo to give professional and other highly skilled athletes a \u201clevel playing field\u201d with the robot, D\u00fcrr said in an interview with The Associated Press. Some of the athletes said they were surprised by Ace\u2019s prowess.<\/p>\n
Sony calls it a first for a common competitive sport<\/p>\n
Sony says it is the \u201cfirst time a robot has achieved human, expert-level play in a commonly played competitive sport in the physical world \u2014 a longstanding milestone for AI and robotics research.\u201d<\/p>\n
The custom-built robot has eight joints that direct its movements, or degrees of freedom, enabling it to position the racket, execute shots and swiftly respond to its opponent\u2019s rallies.<\/p>\n
\u201cSpeed is really one of the fundamental issues in robotics today, especially in scenarios or environments that are not fixed,\u201d said Michael Spranger, president of Sony AI, in an interview.<\/p>\n
\u201cWe see a lot of robots that are in factories that are very, very fast,\u201d Spranger said. \u201cBut they\u2019re doing the same trajectory over and over again. With this technology, we show that it\u2019s actually possible to train robots to be very adaptive and competitive and fast in uncertain environments that constantly change.\u201d<\/p>\n
Spranger said such technology could play a role in manufacturing and other industries. It\u2019s also not hard to imagine how such high-speed and highly perceptive hardware could be used in war.<\/p>\n
Building parity with humans is a challenge<\/p>\n
A humanoid robot\u00a0ran faster than\u00a0the human world record in a half-marathon race for robots in Beijing on Sunday, but getting a machine to interact and compete at split-second speeds with skilled human athletes is in some ways a more difficult challenge.<\/p>\n
Spranger said it was important for researchers to not give the robot too unfair of an advantage and make its speed, arm\u2019s reach and performance comparable to a skilled athlete who trains at least 20 hours a week. It plays by official table tennis rules on a typically sized court.<\/p>\n
\u201cIt\u2019s very easy to build a superhuman table tennis robot,\u201d Spranger said. \u201cYou build a machine that sucks in the ball and shoots it out much faster than a human can return it. But that\u2019s not the goal here. The goal is to have some level of comparability, some level of fairness to the human, and win really at the level of AI and the level of decision-making and tactics and, to some extent, skill.\u201d<\/p>\n
That means, he said, that \u201cthe robot cannot just win by hitting the ball faster than any human ever could, but it has to win by actually playing the game.\u2033<\/p>\n
AI researchers have long used board games like chess as benchmarks for a computer\u2019s capabilities. They later moved into more open-ended\u00a0video game worlds. But moving AI from simulated environments to the physical world has long been the gold standard for robot makers.<\/p>\n
The past year has marked a \u2033kind of ChatGPT moment for robotics,\u201d Spranger said, with new, AI-driven approaches to teach robots about their real-world environments and task them with physically demanding activities, like backflips.<\/p>\n
\u2018Ace\u2019 pulled off shots pros thought were impossible<\/p>\n
Sony is hardly the first to tackle robots in table tennis. John Billingsley helped pioneer such contests in 1983 in a paper titled \u201cRobot Ping-Pong.\u201d More recently, Google\u2019s AI research division DeepMind has also tackled the sport.<\/p>\n
And while impressive, Billingsley said Sony\u2019s all-seeing computer vision and motion detection capabilities make it hard for a two-eyed human to stand a chance.<\/p>\n
\u201cI would not want to belittle the achievement, but they have gone at the task mob-handed, and used sledgehammer techniques,\u201d Billingsley, a retired mechatronics professor at the University of Southern Queensland in Australia, said in an email to the AP.<\/p>\n
He added, however, that it adds to the lesson that \u201ctrue progress comes out of contests, whether they involve hitting a ball or setting foot on Mars.\u201d<\/p>\n
Japanese professional players Minami Ando and Kakeru Sone were among those who competed against Sony\u2019s robot. Two umpires from the Japanese Table Tennis Association judged the games.<\/p>\n
After submitting the paper to peer review ahead of its publication in Nature, Sony researchers kept experimenting and said Ace accelerated its shot speeds and rallies and played even more aggressively and closer to the table edge. Competing against four high-skill players, Sony said Ace defeated all but one of them in December.<\/p>\n
Another expert player, Kinjiro Nakamura, who competed in the 1992 Barcelona Olympics, told researchers after observing Ace play a shot that \u201cno one else would have been able to do that. I didn\u2019t think it was possible.\u201d<\/p>\n
But the robot now having done it \u201cmeans that there is a possibility that a human could do it too,\u201d he said, in remarks published in the Nature paper.<\/p>\n
___<\/p>\n
AP journalists Yuri Kageyama and Javier Arciga contributed to this report.<\/p>\n
#Meet #Ace #paddlewielding #robot #beat #humans #ping #pong #breakthrough<\/p>\n","protected":false},"excerpt":{"rendered":"
A paddle-wielding robot is so adept at playing table tennis that it is posing a…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[245],"tags":[9621,1659,2750,2571,2316,9622,9623,9624,4422,2916],"_links":{"self":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts\/4572"}],"collection":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4572"}],"version-history":[{"count":0,"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts\/4572\/revisions"}],"wp:attachment":[{"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4572"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4572"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4572"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}