Sony AI robot beats players as humanoid robot wins Beijing race

An autonomous desk tennis robot developed by Sony AI has competed towards and defeated high-level human players in regulated matches, in accordance with Reuters. The system is a part of a broader class typically referred to as “physical AI,” the place synthetic intelligence is utilized to machines working in real-world environments.

The robot, named Ace, was designed to function in a aggressive sport atmosphere that requires fast decision-making and exact motor management. According to the venture group, it combines high-speed notion techniques with AI-driven management to execute pictures underneath match circumstances.

Ace competed in matches carried out underneath International Table Tennis Federation guidelines and officiated by licensed umpires. In trials documented in April 2025, the system gained three out of 5 matches towards elite players and misplaced two towards professional-level opponents. Sony AI reported that subsequent matches in December 2025 and early 2026 included wins towards skilled players.

Previous desk tennis robots have existed because the Nineteen Eighties, however they weren’t in a position to match the efficiency of superior human players. “Unlike pc video games, the place prior AI techniques surpass human consultants, bodily and real-time sports activities like desk tennis stay a serious open problem,” stated Peter Dürr, director at Sony AI Zurich and lead of the venture.

AI techniques have achieved sturdy ends in digital environments like chess and video video games, the place circumstances are totally simulated, Dürr stated.

Dürr stated the system was developed to review how robots can reply with velocity and accuracy in dynamic environments. The work was detailed in a research printed within the journal Nature.

The sport presents technical challenges as a result of velocity and variability of the ball, together with complicated spin and altering trajectories, which require fast sensing and coordinated motion in tight time constraints, Dürr stated. Ace’s structure contains 9 synchronised cameras and three imaginative and prescient techniques, which monitor the ball’s motion and spin. The system processes visible knowledge at a velocity ample to seize movement that’s tough for the human eye to resolve. “This is quick sufficient to seize movement that may be a blur to the human eye,” Dürr stated.

The robotic platform makes use of eight joints to regulate the racket. Three management positioning, two management orientation, and three handle shot power and velocity. The configuration was designed to fulfill the minimal mechanical necessities for aggressive play.

Unlike many AI techniques educated by means of human demonstration, Ace was educated in simulation. The strategy allowed it to develop its personal methods, leading to play patterns that differ from human opponents. Dürr stated the system “learns to play not from watching people” however by means of self-training in simulated environments.

Professional participant Mayuka Taira, who misplaced a match to the system, stated the robot was tough to foretell as a result of it exhibits no seen cues throughout play. Rui Takenaka, an elite participant who each gained and misplaced towards Ace, stated it dealt with complicated spins properly however was extra predictable on easier serves. Taira stated the system’s lack of emotional indicators made it more durable to anticipate its responses. “Because you may’t learn its reactions, it’s unattainable to sense what sort of pictures it dislikes or struggles with,” she stated.

Dürr stated the system demonstrates sturdy potential in studying ball spin and reacting shortly, whereas ongoing work focuses on bettering adaptability throughout matches. The venture group stated comparable notion and management strategies might be utilized to areas like manufacturing and repair robotics.

Humanoid robots examined in long-distance race

At the 2026 Beijing E-Town Humanoid Robot Half Marathon, humanoid robots competed over a 21-kilometre course in Beijing. The occasion included greater than 100 robots and roughly 12,000 human members, who ran on separate tracks.

A robot named Lightning, developed by Honor, accomplished the race in 50 minutes and 26 seconds. The time was sooner than Olympic runner Jacob Kiplimo’s 57 minutes and 20 seconds recorded on the Lisbon Half Marathon in March. Lightning collided with a barricade in the course of the race however continued and completed first. Honor robots additionally positioned second and third within the competitors. Performance improved in comparison with the earlier yr’s occasion, the place the quickest robot accomplished the course in two hours, 40 minutes and 42 seconds. Organisers stated the occasion was meant to check humanoid robots in large-scale, real-world circumstances.

According to Associated Press, one other Honor robot accomplished the course in 48 minutes underneath distant management. However, race guidelines prioritised autonomous navigation, and Lightning was recognised as the official winner.

Honor engineers stated applied sciences developed for the robot, together with structural reliability and liquid-cooling techniques, might be utilized in industrial eventualities.

(Photo by Mattias Banguese)

See additionally: Cadence expands AI and robotic partnerships with Nvidia, Google Cloud

Want to study extra about AI and large knowledge from trade leaders? Check out AI & Big Data Expo happening in Amsterdam, California, and London. The complete occasion is a part of TechEx and co-located with different main expertise occasions. Click here for extra data.

AI News is powered by TechForge Media. Explore different upcoming enterprise expertise occasions and webinars here.

The submit Sony AI robot beats players as humanoid robot wins Beijing race appeared first on AI News.