Iván Hernández Dalas: Sony AI table tennis robot outplays elite human players

Ace rotates its paddle as it prepares to return the ball back to its human opponent, Yamato Kawamata, during a match in December 2025. Credit: Sony AI.

In an article published today in Nature, Sony AI introduce Ace, the first robot to beat elite human players in competitive physical sport.

Although AI systems have shown advanced performance in digital domains and board games (such as complex video games, chess and Go), translating this to physical performance has remained a significant challenge. Such a feat requires perception, planning, and control to work in a high-speed domain on the scale of milliseconds. Table tennis is a demanding and complex real-world test for robotics, requiring rapid decision-making, precise physical execution, and continuous adaptation to an unpredictable opponent. The ball’s high speed, spin, and complex trajectories are central to competitive play.

Director of Sony AI in Zürich, and project lead for Ace, Peter Dürr said “this research has shown that an autonomous robot can, in fact, win at a competitive sport, matching or exceeding the reaction time and decision making of humans in a physical space. Table tennis is a game of enormous complexity that requires split-second decisions as well as speed and power. This research breakthrough highlights the potential of physical AI agents to perform real-time interactive tasks, and represents a significant step toward creating robots with broader applications in fast, precise, and real-time human interactions.”

A complete view of table tennis robot, Ace, including arm and track. Credit: Sony AI.

What new components does Ace incorporate?

Ace combines event-based vision sensors and a control system based on model-free reinforcement learning, as well as state-of-the-art high-speed robot hardware. Ace was designed with three novel components:

  • A high speed perception system composed of nine active pixel sensor cameras to determine the ball’s precise 3D position, combined with three gaze control systems that use event-based vision sensor cameras, pan/tilt mirrors, and telephoto tunable lens to measure the ball’s angular velocity and spin in real time.
  • A novel control system based on model-free reinforcement learning to enable rapid adaptation and decision-making without reliance on pre-programmed models.
  • High-speed robotic hardware capable of executing precise, high-speed control for agile physical interaction.

Members of the Ace research team and table tennis officials pose with the robot and its human opponent, Mayuka Taira, following an official match in December 2025.

From Figure 4 in the Nature manuscript “Outplaying elite table tennis players with an autonomous robot” this film shows the robot making a split section change to its trajectory when the ball hits the net. Credit: Sony AI and Nature.

Testing Ace against elite players

For the results reported in the Nature publication, Ace was evaluated in matches against five elite players and two professional table tennis players, under International Table Tennis Federation (ITTF) regulations. Ace achieved three victories in five matches against the elite players, along with competitive performances in the remaining matches.

There were some interesting results from the evaluations, including the fact that Ace was able to return a wide range of spins, consistently achieving over 75% return rate up to spins of 450 rad/s. The control systems behind Ace also allowed for quick reaction to unusual shots, such as balls bouncing off the net. This behavior illustrates the ability of the approach to generalize to situations that are both rare and hard to model in simulation.

Following submission of the Nature manuscript, the team conducted additional competitive matches in December 2025 and March 2026, beating professional players in the process. Compared with earlier evaluations, Ace demonstrated higher shot speeds, more aggressive placement closer to the table edge, and faster-paced rallies, reflecting continued performance gains under competitive conditions.

Find out more about the project in this video from Sony AI.



View Source

Popular posts from this blog

Iván Hernández Dalas: 4 Show Floor Takeaways from CES 2019: Robots and Drones, Oh My!

Image
We’ve had some time to recuperate from the madness of CES, in which more than 150,000 attendees and thousands of exhibitors displayed their latest gadgets, gizmos and yes, even robots, on the CES show floor. Last week’s reporter’s notebook focused on the collection of startups around the Eureka Park area of CES, but several of the same trends were evident on the main South Hall 2 area of the Las Vegas Convention Center, where drones, robotics, AR/VR, and gaming took center stage. While most of our time was spent at CES hosting the Service Robots Arrive in Daily Life event, we did have some time during the week to visit the show floor and record observations. Here’s what we saw on the show floor, as well as some of our own individual meetings: 1. Underwater drones make a big splash On the main floor, there was no busier aerial drone booth than the DJI booth, but that is expected given the company’s dominance in the space. But once you got past that, you noticed a lot more drone co...
Read more

Iván Hernández Dalas: How automation and farm robots are transforming agriculture

Image
Source: EOS Data Analytics Agriculture is becoming the most high-tech industry today. All the top-notch technologies are finding a place in the way we produce, harvest, and distribute our crops. And in all cases, farm automation and robots are not an affordable luxury, but a necessary minimum due to tackling the rising global food demand. Agricultural robots can mitigate labor shortages by automating tasks like planting, harvesting, and weeding, while also supporting sustainable practices. Combined with satellite imagery tools for data-driven farming, these innovations can make precision agriculture more efficient, resilient, and environmentally responsible. According to the United Nations report , by 2050, the world will need 70% more food to feed nearly 9.7 billion people. Considering this demand, farm robots and remote sensing are the cornerstone of the proper work of the supply chain. Smart machines arise for the farm Farm robots are no longer experimental concepts — they ...
Read more

Iván Hernández Dalas: Physical Intelligence open-sources Pi0 robotics foundation model

Image
Physical Intelligence, the San Francisco-based startup that has raised more than $400 million , has open-sourced its Pi0 robotic foundation model. Pi0 was introduced a few months ago and can be tuned to a range of tasks, including folding laundry, cleaning a table, scooping coffee beans, and more. Physical Intelligence has released the code and weights for Pi0 as part of its experimental openpi repository on GitHub. It also provides checkpoints for a few “simple tasks” on available platforms such as ALOHA and DROID, example code to run inference on real-world and simulated robot platforms, and the code for fine-tuning the base π0 model for your own tasks and platforms. The company said between 1-20 hours of data was sufficient to tune Pi0 to a variety of tasks in its own experiments. HuggingFace has also prepared a PyTorch port of openpi for those developers who prefer PyTorch over JAX. “We believe that general purpose models that can control any robot to perform any task will b...
Read more