UNIT.City — місце, де люди працюють... КРАЩЕ! Обирай свій простір просто зараз 👉
Олександр КузьменкоRobots
23 April 2026, 15:28
2026-04-23
“He’s very difficult to predict”. Sony’s Ace robot has started beating professional table tennis players
Japan’s Sony Corporation has created the world’s first tennis robot, Ace, capable of competing on equal terms with humans in professional table tennis. It has super-fast AI and precision mechanics that allow it to defeat elite players in real matches.
Japan’s Sony Corporation has created the world’s first tennis robot, Ace, capable of competing on equal terms with humans in professional table tennis. It has super-fast AI and precision mechanics that allow it to defeat elite players in real matches.
The system’s success is based on a combination of high-speed machine vision and artificial intelligence-based control algorithms, Reuters reports. Ace competed against elite athletes under official International Table Tennis Federation (ITTF) rules under the supervision of licensed judges.
Unlike strategy games like chess or Go, where AI has long dominated, real-time physical sports remain a major challenge for machines. According to Peter Dürr, director of Sony AI Zurich and project leader, table tennis requires reactions at the limits of human capabilities due to the complex rotations of the ball and its high flight speed.
«The success of Ace suggests that similar techniques can be applied to other areas that require fast, real-time control—from manufacturing and service robotics to industries where safety is critical,» Dürr notes in an article for the journal Nature.
The robot’s architecture consists of nine synchronized cameras that track the ball’s movement faster than the human eye can. The mechanical part is represented by a platform with eight joints that provide the necessary force and orientation of the racket for competitive shots.
Professional tennis player Mayuka Taira, who lost to Ace, highlighted the specifics of playing against a machine: «He is very difficult to predict and he shows no emotion. It is impossible to understand which shots he does not like or which ones he has difficulty with, and this makes the game even more difficult.»
The developers are currently working on the adaptability of the AI, as professional players are still able to find weaknesses in the robot’s logic by using non-standard serves. However, already in March and April 2026, Ace was able to win a series of victories over top-level players.
Як нейромережі бачать вільну та незалежну Україну? Тест dev.ua
Нейронні мережі для генерації зображень бачать світ по-своєму, їхню логіку зрозуміти часом зовсім неможливо. Але таки хочеться. На честь Дня Незалежності України редакція dev.ua вирішила провести невеликий експеримент.
Ми задали чотирьом різним нейронним мережам п’ять однакових запитів: «прапор України», «День Незалежності України», «український Крим», «перемога України» та «українці». Отриманими результатами ми ділимося з вами нижче.
У TikTok тепер можна генерувати фон за допомогою нейромережі. Ми протестували її та ділимося результатами
У TikTok з’явилася нова функція «Розумний фон». З її допомогою як фон для тіктоків можна підставляти згенеровані нейромережею зображення. Редакція dev.ua протестувала цю технологію і ділиться своїми враженнями.