China's original innovation has delivered the "key winning shot", Galaxy Universal has forged the AstraTennis moment.

On August 22, at the National Speed Skating Oval "Ice Ribbon", a tennis ball crossed the net and flew towards the opposite side at high speed.

Standing on the other side was a humanoid robot.

It fixed its eyes on the incoming ball, moved its steps to adjust its position, then turned its body and swung its racket. The tennis ball was hit back to the half of the court where the human athlete was, launching a multi-shot rally between human and robot.

This is a scene from the opening ceremony of the 2nd World Humanoid Robot Games. Galaxy Universal Robot competed on the same field with top tennis players, completing autonomous running and hitting under the live broadcast lens of China Media Group. In the singles session, it needs to judge the ball path independently; after entering the doubles, it also collaborates with human teammates in real time, dynamically adjusts strategies according to the situation on the court, and even makes extreme saves in high-speed offense and defense.

This live broadcast of the large-scale event has achieved a milestone breakthrough on a global scale, fully presenting the fully autonomous tennis rally of humanoid robots. It also pioneered the realization of robots' autonomous perception, autonomous decision-making and autonomous action on the real competition field, to carry out real-time confrontation and cooperative game with human athletes.

Ten years ago, in 2016, AlphaGo defeated Lee Sedol on the chessboard, making artificial intelligence enter the public view in a shocking way for the first time. Ten years later, Galaxy Universal Robot autonomously caught a tennis return from a world-renowned player on the field, presenting the world with the AstraTennis moment of embodied intelligence.

This time, this iconic moment was created by China, and it has become the most hardcore declaration of China's original technological innovation.

1. More than Similar in Appearance, Tennis Becomes a Hardcore Examination for Embodied Intelligence

This year's Humanoid Robot Games is grand in scale. According to the official event materials, a total of 2056 robots participated in the conference. 51 events including running, martial arts, football and table tennis are all testing the motion limits of humanoid robots.

Tennis is not included in the official competition events of this year's Games, but presented in the form of an opening ceremony exhibition match.

This is not because this sport is too early for robots — on the contrary, it is because Galaxy Universal is currently the only player in the world that can bring fully autonomous tennis confrontation to the real competition field. The setting of rules has to wait for enough participants to complete the match list. Galaxy Universal chose to give the only opponent on this match list to a real human tennis player.

On the football field, robots have time to adjust their positions; the hitting area of table tennis is relatively fixed, which mainly tests the upper body. In contrast, tennis requires robots to catch up with high-speed incoming balls while running across the whole court, maintain balance and swing the racket accurately, and adjust strategies in real time according to the changes of opponents, which puts almost harsh requirements on whole-body control and autonomous decision-making.

In other words, humanoid robots have been able to complete a whole tennis game in a way close to human athletes, and what the audience can intuitively feel most on the court is the full sense of realism it shows.

When an incoming ball is pressed to the corner, it will not stand in place and swing hastily, but move laterally first, then use a series of small steps to find the hitting position. After the body's center of gravity stabilizes, the torso turns accordingly, and the racket swings towards the incoming ball. Facing a more tricky landing point, it will even run across most of the court to complete the save when it is almost out of balance. Serving, receiving and forehand-backhand switching are connected into a set of natural movements.

"Being like a human" is only the first step, and more importantly, "understanding tennis".

During the baseline rally, the robot will control the landing point of the return ball according to the position of the opponent; when an opportunity ball appears, it can move to the net and change the hitting method. In singles, it independently organizes the offense and defense of each shot; after entering doubles, it can observe the position of its teammates, judge who should handle the ball, and make up for the gaps on the court in time.

More interestingly, robots do not have psychological fluctuations like human athletes. No matter whether the score is leading or falling behind, it remains unhurried, and will not affect subsequent judgments due to mistakes, but always focus on how to hit the next ball and how to fight for the next point.

The live broadcast lens further magnifies the gold content of this technology. Demonstrations in the laboratory can be shot repeatedly, but the incoming balls on the real court will not strictly follow the training script. When facing world-class athletes, the robot has to give a quick response to every shot.

This is the AstraBrain Latent technology released by Galaxy Universal Robot in March this year, which demonstrated for the first time the high-dynamic and long-range tennis rally between humanoid robots and real humans. This video once made the overseas tech circle doubt their own eyes. Elon Musk, CEO of Tesla, also responded on social platforms, while Andrej Karpathy, former head of AI at Tesla, said that when he first saw the video, he even suspected that the footage was AI-generated.

Today, on the global event live broadcast, Galaxy Universal has responded to all doubts with an excellent performance.

2. Big and Small Brain Coordination, the Technological Leap Behind AstraTennis

Anyone who has played tennis knows that tennis is a sport that pushes both thinking and action to the limit, and so do robots: it not only needs to understand the game and make decisions, but also allows the body to execute accurately in high-speed confrontation.

Supporting all this is Galaxy AstraBrain, the embodied intelligence large model independently developed by Galaxy Universal, which is also the world's first embodied large model that integrates brain, cerebellum and neural control.

In the system of Galaxy AstraBrain, the "big brain" is responsible for understanding and decision-making, it observes incoming balls and understands the game situation, decides what kind of return strategy to adopt, and thinks about how to win the game. The "cerebellum" solves the problem of how to coordinate the whole body within milliseconds, so that the robot can complete movement, balance and racket swing.

Tennis hitting occurs in an extremely short time window. Robots need to complete whole-body dynamic balance while running at high speed, so that legs, torso, arms and even wrists are highly coordinated to complete the swing with sufficient explosive power and accuracy. Driven by the cerebellum, the robot's movements are no longer mechanical and fragmented instruction execution, but can present a more anthropomorphic, smooth and highly dynamic motion state.

However, only with the coordination of big brain and cerebellum is not enough for the robot to reach such a level. The more critical question is: Where on earth do robots learn these capabilities?

When a person learns tennis, he usually practices swinging and footwork first, and then forms a sense of the ball through a large number of rallies, but it is difficult for robots to obtain a sufficiently complete set of learning materials.

One way is to record professional athletes playing tennis, but this requires high-precision motion capture in a large range of venues. When swinging the racket quickly, the subtle changes of the wrist and racket surface must also be accurately recorded. Even if complete human motion is collected, there are still differences between the robot's joint structure and motion range and that of humans, so it is difficult to copy directly.

The special feature of Galaxy AstraBrain is that it can learn from imperfect human data, and allow robots to learn and reflect through millions of times of human prior experience in the virtual tennis world, while carrying out multi-agent game and sparring, so that robots can realize the emergence of skills and migrate to the physical world.

After these "imperfect" data enter Galaxy Universal's core technology platform "Galaxy AstraForge", they will continue to be amplified in the virtual world. The platform can convert scattered human movements into data that robots can learn, and continuously generate training tasks under different ball speeds, landing points and opponent conditions.

According to Wang He, founder and CTO of Galaxy Universal, the training time accumulated by robots in the virtual tennis world is equivalent to that of humans playing tennis continuously day and night for decades.

More interestingly, multiple virtual robots can also practice with each other. They try different running routes and hitting strategies in a large number of rounds, and continue to adjust according to the results. Robots thus gradually master continuous hitting, baseline mobilization and landing point control, and begin to learn how to create scoring opportunities in the game.

In other words, human data tells the robot what the movement should roughly look like, and reinforcement learning helps it find the implementation method suitable for its own body.

3. AI Begins to Challenge Complex Games in the Real World

In a sense, AstraTennis and AlphaGo form a technical echo spanning ten years, and also reflect the difference between the two generations of artificial intelligence paradigms.

AlphaGo relies on massive chess games and self-game to complete strategic games in a closed and deterministic digital chessboard space, proving that AI can beat top human players in a world with clear rules, opening the era of deep game AI. But within the chessboard, everything is limited to symbols and deduction; while AstraTennis pushes game intelligence from the virtual digital space into the real physical world full of noise, disturbance and uncertainty.

Robots no longer only do paper deduction, but must simultaneously complete environment perception, situation decision-making, whole-body dynamic control and complex physical interaction. Intelligence no longer stops at thinking, but needs to complete the closed loop of "cognitive decision-making + whole-body execution". This double test of highly bound thinking and body, which seems to be the basic requirement of sports scenes, is the core barrier that has long been lying in front of the industrialization of embodied intelligence, and it is also a technical problem that the global industry has always been difficult to break through.

If we want robots to truly adapt to the real physical world, we must not only overcome the algorithm problem of intelligent decision-making, but also solve the implementation pain points of precise body execution and dynamic environment adaptation, which also makes the industry trapped in various practical bottlenecks for a long time: high-quality physical interaction data is scarce, complete human movements cannot be directly reproduced to the robot body, and a large number of solutions still stay in laboratory scripted demonstrations, which are difficult to withstand the real test of public live broadcast.

In view of the implementation dilemma of the whole industry, Galaxy Universal's technical path gives a key breakthrough idea: rely on imperfect human prior data for enlightenment, complete skill emergence through millions of multi-agent games on the virtual tennis court, and then complete the migration to reality; the integrated architecture of big brain and cerebellum opens up the complete link from high-level cognitive decision-making to millisecond-level whole-body motion control, fundamentally solving the industry pain points of disconnection between decision-making and execution and poor adaptability to real scenes.

When humanoid robots can independently complete a complete set of tennis games in the live broadcast of large-scale events, its value has long gone beyond the matter of playing tennis itself. This technology base tempered by high-dynamic confrontation has general migration potential: a large number of sample learning reduces the data threshold of complex tasks; self-game acquires the logic of collaboration and confrontation; virtual training allows robots to accumulate massive experience before landing in reality; the coordination of big brain and cerebellum enables intelligence to be truly transformed into stable and reusable behaviors. This means that a large number of unstructured tasks that highly rely on human experience, such as home assistance, industrial operation and medical assistance, are entering the solvable territory of embodied intelligence.

Objectively speaking, compared with professional athletes, robots still have room for improvement in hitting explosive power and tactical diversity. However, realizing continuous autonomous confrontation with human athletes on an unscripted public court has marked that global humanoid robots have crossed a key technical inflection point: embodied intelligence is no longer just a single-point demonstration, but begins to have the ability to continuously complete long-sequence complex tasks in real and uncontrollable scenes.

Looking at the global track, most teams still follow the splicing route of large model plus off-the-shelf controllers, while Galaxy Universal chooses to start from the bottom layer of embodied intelligence, fully build a native technical chain from "big brain" task understanding game decision-making to "cerebellum" whole-body real-time motion control, and choose tennis, a real confrontation scene with extremely high difficulty, to complete centralized verification.

This is the industry weight of the "AstraTennis moment". It is not only a single-point technical achievement of an enterprise, but also represents that the Chinese team has embarked on an independent exploration path of original innovation on embodied intelligence, the next-generation core AI track.

The highlight moments of AI in the past ten years were mostly born in overseas laboratories, but today, local Chinese teams are producing globally discussed original breakthroughs in the field of physical intelligence, pushing the capability boundary of AI from closed chessboards to a broader and more complex real world.

AstraTennis has thus become an embodied intelligence milestone presented by China's original technology and witnessed by the whole world.