Google DeepMind says its table-tennis robot reached amateur human-level performance in competitive rallies—but that does not mean it played as well as every human. In 29 matches against people across skill levels, the robot won 45% of matches overall, could not serve under the test rules, and lost every match against advanced and advanced-plus opponents.
What did Google DeepMind’s robot achieve?
The system played full competitive table-tennis matches against human opponents it had not encountered before. Google DeepMind describes it as the first learned robot agent to reach amateur human-level performance in competitive table tennis. Its more specific assessment is that the results suggest intermediate-level human play on rallies—not elite or professional play. Google DeepMind’s project overview reports the evaluation and its limits.
As an Amazon Associate I earn from qualifying purchases.
That distinction matters: the achievement is not simply that a machine returned a few balls. It used physical movement, sensing, and shot selection to compete in rallies, then adapted its choices based on match statistics and what it learned about its opponent.
Quick wins for a faster PC:
Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Repair Windows errors before they cause bigger problemsFix Now →Scan for outdated or missing drivers - takes under a minuteDriver Scan →How did it perform against human opponents?
Google DeepMind reports 29 robot-versus-human matches. A professional table-tennis coach determined the players’ skill levels. The team reports match and game win rates overall, along with match results by opponent tier:
#1 Best Overall
- Smart Table Tennis Robot -Our "NOVA S Pro" equipped with 2 BASF ball throw wheels. Frequency:30-90 balls/min, max 0.66s/ball, 11-level. Speed:Max 15m/s, 21-level. 9 types of spin. Rotation speed:60r/s, 21-level. Support count, combo, double bounce ball serving.
- APP & Remote Control -Experienceunparalleled flexibility with our ping pong ball machine that can be controlled via an app or remote control. Tweak spin, rotation intensity, landing point, ball speed, hight and frequency to personalize your workout.
- Built-in Preset and Customizable Training Drills -264 built-in preset training drills, and also allows for programming custom drills, making it the perfect tool for both beginner and advanced players to create a personalized training experience.
- Landing Spot Simulated Animation -Experience precise landing spot control with our "Pongbot" app's simulated animation, designed to help you hit the ball where it counts and allowing you to customize placement for perfecting your return shots.
- Portability and Innovation -Our robot is versatile, with an innovative near-net serve trajectory that makes it ideal for mastering mid and aggressive game techniques through short-range simulations.
| Evaluation result | Reported outcome |
|---|---|
| Matches played | 29 |
| Matches won overall | 45% |
| Games won overall | 46% |
| Matches won against beginners | 100% |
| Matches won against intermediate players | 55% |
| Matches won against advanced and advanced-plus players | 0 |
These figures come from the project team’s evaluation; they are not an independent tournament certification. The sharp drop against stronger players is central to interpreting the headline: the robot could compete successfully with some amateur opponents, but it did not beat the advanced players in the study.
How was the robot built to play?
The system combined a set of learned, specialized skills with a high-level controller. Low-level policies handled particular actions, including forehand topspin, backhand targeting, and forehand serve. The high-level controller selected among skills using their descriptors, match statistics, and information gathered about the opponent.
Rank #2
- Includes a net that simplifies the setup process
- Can be controlled via a remote or a smartphone app, giving the user multiple options
- Comes programmed with 264 drills, providing a broad range of training possibilities
- Enables the user to create custom drills, making it a versatile tool
- Perfect for players of all skill levels, including beginners and advanced players alike
Its development loop combined human-human play data, simulation, and deployment on real hardware. The team also collected task-condition data during play and describes the agent adapting to previously unseen opponents. Table tennis served as a demanding test of fast movement, real-time decisions, precise control, and direct interaction with a human—not just a demonstration of isolated shots.
Why couldn’t it beat advanced players?
Google DeepMind says stronger opponents exploited weaknesses in the robot’s policies, especially when using underspin. Low balls are difficult for the robot to reach without colliding with the table, and determining spin in real time is also challenging. Those problems can constrain both where the robot can move and which response it should choose.
Rank #3
- JOOLA - AN OLYMPIC TABLE TENNIS BRAND TRUSTED FOR 60 plus YEARS: Launched in the 1950s, JOOLA has been the proud sponsor of the biggest tournaments in the world, including the Olympics, World Championships, and US Open; Equipment designed for all levels
- WIRELESS REMOTE WITH MEMORY BUTTON: Control the ping pong robot from the other side of the table tennis table; Make changes to your practice on the fly or let your coach take the reins; Create fun ping pong games for kids or adults
- CONTROL FREQUENCY, BALL SPEED, DIRECTION, and SPIN: Just like a real opponent your ping pong machine can keep you guessing; Adjust the shooter increase or decrease the balls, change the oscillation to side to side, add topspin or backspin, and ball speed
- SUPER FAST ASSEMBLY: Just twist on the ping pong ball feeder to the shooter and you are ready to play some table tennis games; iPONG doesn't require any app downloads or complicated instructions, it is as simple as flipping a switch
- SHOOTS UP TO 70 BALLS PER MINUTE: Meet your new multi-ball coach; Ping pong ball frequency can be slowed to 30 and as fast as 70; Used by professionals and beginners, the iPONG V300 is the table tennis equipment you need to become a champion
The project’s results therefore reflect the interaction between its learned strategy and its physical setup. A shot that looks manageable to a person may still be difficult for a robot that must sense the ball, infer its spin, move its paddle into position, and avoid the table within a short time.
What were the match rules and user reactions?
Participants played three games against the robot under standard rules with modifications because the robot was physically unable to serve. The match results should therefore be read as competitive play under that altered setup, not as proof that the system could play an unmodified match from the opening serve.
Rank #4
- "OMNI S Pro" table tennis robot with remote "E Pad S" and App "Pongbot" for dual control and versatility.
- Programmable ping pong robot: customizable settings simulate ball speed, spin, frequency, trajectory, and landing.
- 396 pre-saved ball trajectories for quick start - 66 drills x 3-star rating x forehand/backhand mode options.
- App with open drill library for visual routines that can be shared and customized, allowing users to freely train and learn from each other.
- In the package: OMNI S Pro unit, ball recycling net, E Pad S, power adapter, and user manual. Not included: 40mm/40mm+ balls.
Google DeepMind also reports that participants rated the robot highly for fun and engagement, wanted to play again, and spent an average of 4 minutes and 6 seconds of a five-minute free-play period playing it. The project overview does not state how many participants contributed to those responses.
Recommended Free Tools
Is the robot available to buy?
The project describes a research system, its evaluation, and related research materials; it does not identify the robot as a retail product. The reported results are findings from Google DeepMind’s own study, not an independent competition or certification. For the same reason, “as well as a human” should be understood as a qualified claim about amateur-level performance on rallies, rather than a claim of parity with humans at every skill level.
Futurism’s August 11, 2024 report framed the announcement as a robot that plays ping pong “as well as a human.” The project team’s own description supplies the important qualification: amateur-level competitive performance, with intermediate-level play indicated on rallies and clear weaknesses against advanced opponents.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
