Loading video...

Video Failed to Load

Go Home

Sony's Project Ace has created the first robot to beat an elite human table tennis player, with nine cameras analyzing spin and tracking the ball in real time.

CNET's profile picture

CNET

2,676,700 subscribers

15,098 views • 1 month ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Sony's AI robot just beat professional table tennis players. 9 cameras. Reads the ball's spin by tracking the logo. They handicapped it on purpose. It still won. 💀
0:22

Sony's AI robot just beat professional table tennis players. 9 cameras. Reads the ball's spin by tracking the logo. They handicapped it on purpose. It still won. 💀

Min Choi

44,095 views • 3 months ago

This AI-powered robot just beat an elite table tennis player via The Guardian
0:20

This AI-powered robot just beat an elite table tennis player via The Guardian

internet hall of fame

191,792 views • 3 months ago

Sony robot is able to beat 3 out of 5 "elite" table tennis players but loses to 2 professional players. Robot has latency of ~20ms vs ~230ms for an elite human player. Nature paper: Github:
0:23

Sony robot is able to beat 3 out of 5 "elite" table tennis players but loses to 2 professional players. Robot has latency of ~20ms vs ~230ms for an elite human player. Nature paper: Github:

pfung

58,182 views • 3 months ago

A robot has beaten humans in a real sport — and it’s no longer a joke Japan’s Sony has created a robot called Ace that has reached the level of strong table tennis players. In 2025, it won three out of five matches against top-level opponents and later began consistently defeating professionals. Ace tracks the ball using cameras and hits so fast that humans can’t keep up. Players admit it’s hard to read, as the robot shows no emotions and behaves in unconventional ways.
2:03

A robot has beaten humans in a real sport — and it’s no longer a joke Japan’s Sony has created a robot called Ace that has reached the level of strong table tennis players. In 2025, it won three out of five matches against top-level opponents and later began consistently defeating professionals. Ace tracks the ball using cameras and hits so fast that humans can’t keep up. Players admit it’s hard to read, as the robot shows no emotions and behaves in unconventional ways.

NEXTA

45,810 views • 3 months ago

The robot, known as Ace, beat three out of five elite table tennis plates who had more than ten years of training, and scored 48 versus 70 in two defeats to professionals.
0:39

The robot, known as Ace, beat three out of five elite table tennis plates who had more than ten years of training, and scored 48 versus 70 in two defeats to professionals.

Financial Times

191,853 views • 3 months ago

Sony AI just published the first autonomous robot to beat elite humans at a competitive physical sport. Its name is Ace. The sport is table tennis. The paper dropped in Nature today. 9 cameras triangulate the ball in 3D. Three systems zoom in on the ball's logo mid-flight to read its spin axis. End-to-end reaction time is around 20 milliseconds, roughly 10x faster than a human. It learned by playing itself for 3,000 hours in simulation. No human demonstrations. In April 2025, Ace beat 3 of 5 elite players and lost to both pros. By December, it had beaten a pro. At one point, Ace returned an impossible backspin shot. Kinjiro Nakamura, a 1992 Barcelona Olympian, watched from the side: "No one else would have been able to do that. I didn't think it was possible. But the fact that it was possible means there is a possibility that a human could do it too."
1:00

Sony AI just published the first autonomous robot to beat elite humans at a competitive physical sport. Its name is Ace. The sport is table tennis. The paper dropped in Nature today. 9 cameras triangulate the ball in 3D. Three systems zoom in on the ball's logo mid-flight to read its spin axis. End-to-end reaction time is around 20 milliseconds, roughly 10x faster than a human. It learned by playing itself for 3,000 hours in simulation. No human demonstrations. In April 2025, Ace beat 3 of 5 elite players and lost to both pros. By December, it had beaten a pro. At one point, Ace returned an impossible backspin shot. Kinjiro Nakamura, a 1992 Barcelona Olympian, watched from the side: "No one else would have been able to do that. I didn't think it was possible. But the fact that it was possible means there is a possibility that a human could do it too."

The Rundown AI

61,601 views • 3 months ago

UBTech Robotics has showcased its humanoid robot Walker S2 playing tennis with a human. Using real-time vision sensors, it tracks the ball, adjusts its position, and returns shots with good accuracy. The robot can also swap its own batteries, allowing it to operate continuously without human help.
0:33

UBTech Robotics has showcased its humanoid robot Walker S2 playing tennis with a human. Using real-time vision sensors, it tracks the ball, adjusts its position, and returns shots with good accuracy. The robot can also swap its own batteries, allowing it to operate continuously without human help.

Space and Technology

16,121 views • 3 months ago

Sense. Decide. Act. In milliseconds. This is the story of a robot that can beat professional table tennis players. Watch the short film: #SonyAI #Ace #Robotics
0:43

Sense. Decide. Act. In milliseconds. This is the story of a robot that can beat professional table tennis players. Watch the short film: #SonyAI #Ace #Robotics

Sony AI

22,948 views • 3 months ago

An AI-powered robot has learnt to beat elite amateur human players at table tennis 🏓 The feat has been hailed as a milestone and a true test for robotics, as the sport requires quick reactions and perception-skills, which aren't things robots are usually known for. 📺 The race to create the ultimate AI - watch Global Eye on YouTube:
1:06

An AI-powered robot has learnt to beat elite amateur human players at table tennis 🏓 The feat has been hailed as a milestone and a true test for robotics, as the sport requires quick reactions and perception-skills, which aren't things robots are usually known for. 📺 The race to create the ultimate AI - watch Global Eye on YouTube:

BBC World Service

11,004 views • 3 months ago

This robot isn’t just playing table tennis — it’s sometimes beating human pros, a major leap for machines in the real world.
1:09

This robot isn’t just playing table tennis — it’s sometimes beating human pros, a major leap for machines in the real world.

The Associated Press

82,314 views • 3 months ago

🎾Your humanoid tennis player is here!🤖 Introducing LATENT (Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data) — the world’s first real-time whole-body planning and control algorithm for athletic humanoid tennis. For the first time, a humanoid robot can sustain high-dynamic, long-horizon tennis rallies with millisecond-level reactions, precise ball striking, and natural whole-body motion. This marks a leap from mechanical motion imitation to intelligent, decision-driven athletic interaction. #Galbot #Robotics #Innovation #AI #Technology #Humanoid
1:25

🎾Your humanoid tennis player is here!🤖 Introducing LATENT (Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data) — the world’s first real-time whole-body planning and control algorithm for athletic humanoid tennis. For the first time, a humanoid robot can sustain high-dynamic, long-horizon tennis rallies with millisecond-level reactions, precise ball striking, and natural whole-body motion. This marks a leap from mechanical motion imitation to intelligent, decision-driven athletic interaction. #Galbot #Robotics #Innovation #AI #Technology #Humanoid

Galbot

45,818 views • 4 months ago

Researchers developed Hitter, a humanoid robot that can play table tennis in real-world settings. It was trained on the Unitree G1 robot to predict the ball’s path, choose the right shot, and react in less than a second. In tests, it achieved 106 consecutive shots with a human and even rallied with another humanoid robot.
0:30

Researchers developed Hitter, a humanoid robot that can play table tennis in real-world settings. It was trained on the Unitree G1 robot to predict the ball’s path, choose the right shot, and react in less than a second. In tests, it achieved 106 consecutive shots with a human and even rallied with another humanoid robot.

Space and Technology

25,736 views • 3 months ago

Sony’s AI table tennis robot Ace just straight-up smoked professional human players in real matches under official rules Nature just dropped the study, ping pong is cooked! The future is here, and now it’s got a paddle of all things.
0:32

Sony’s AI table tennis robot Ace just straight-up smoked professional human players in real matches under official rules Nature just dropped the study, ping pong is cooked! The future is here, and now it’s got a paddle of all things.

Mario Nawfal

26,705 views • 3 months ago

What if tennis ball machines were actually smart? While in New York, I went to try the Aceii One for myself. It uses AI and ball tracking technology to rally more like a human, drill more like a coach, and provide feedback to the player. #PaidPartner
1:15

What if tennis ball machines were actually smart? While in New York, I went to try the Aceii One for myself. It uses AI and ball tracking technology to rally more like a human, drill more like a coach, and provide feedback to the player. #PaidPartner

Gill Gross 🦣

73,206 views • 11 months ago

'LATENT' learns tennis skills for humanoid robots from human motion data. The robot can sustain multi-shot rallies, handle ball speeds of 15+ m/s, and showed a 90.9% success rate for the forehand. No onboard cameras or vision models, relies on external MoCap for high-precision, low-latency ball tracking. Paper:
1:31

'LATENT' learns tennis skills for humanoid robots from human motion data. The robot can sustain multi-shot rallies, handle ball speeds of 15+ m/s, and showed a 90.9% success rate for the forehand. No onboard cameras or vision models, relies on external MoCap for high-precision, low-latency ball tracking. Paper:

The Humanoid Hub

63,824 views • 5 months ago

A robot named Ace just became the first AI to outperform human athletes in ping-pong.
0:30

A robot named Ace just became the first AI to outperform human athletes in ping-pong.

Big Brain AI

18,975 views • 3 months ago

🎾 For the first time in its history, Wimbledon has no human line judges. Instead, they're using Hawk-Eye cameras to decide whether the ball is in or out... and it's been making headlines 🎧
1:37

🎾 For the first time in its history, Wimbledon has no human line judges. Instead, they're using Hawk-Eye cameras to decide whether the ball is in or out... and it's been making headlines 🎧

BBC World Service

93,464 views • 1 year ago

Meet our AI-powered robot that’s ready to play table tennis. 🤖🏓 It’s the first agent to achieve amateur human level performance in this sport. Here’s how it works. 🧵
0:40

Meet our AI-powered robot that’s ready to play table tennis. 🤖🏓 It’s the first agent to achieve amateur human level performance in this sport. Here’s how it works. 🧵

Google DeepMind

785,170 views • 2 years ago

🤖 The first 3-on-3 humanoid robot football match just took place in Beijing It was the final of China's RoBoLeague, featuring robots from top universities — including Tsinghua. The bots relied entirely on their own algorithms to decide where to run, how to dodge opponents, and when to strike the ball. Each player used cameras and sensors to detect the ball, field, and rivals — making real-time decisions with zero human input. ⚽️ Dressed in black and purple jerseys, the mechanical footballers clumsily ran, fell, got back up — and kept fighting until the end. The match ended with a 5:3 win for team Volcano.
1:12

🤖 The first 3-on-3 humanoid robot football match just took place in Beijing It was the final of China's RoBoLeague, featuring robots from top universities — including Tsinghua. The bots relied entirely on their own algorithms to decide where to run, how to dodge opponents, and when to strike the ball. Each player used cameras and sensors to detect the ball, field, and rivals — making real-time decisions with zero human input. ⚽️ Dressed in black and purple jerseys, the mechanical footballers clumsily ran, fell, got back up — and kept fighting until the end. The match ended with a 5:3 win for team Volcano.

NEXTA

71,688 views • 1 year ago

We break down all the biggest winners, losers, highlights and robot fails from the first ever World Humanoid Robot Games held in China.
3:18

We break down all the biggest winners, losers, highlights and robot fails from the first ever World Humanoid Robot Games held in China.

CNET

10,895 views • 11 months ago