Realtime AI News
World-First: Robot Takes on Human Tennis Player, Making Extreme Saves and Instant Recovery
A robot has faced a human tennis player in what QbitAI calls a world-first matchup, pulling off extreme ball saves and instantly springing up after falls. The "AstraTennis moment" highlights advances in motion control and dynamic balance that could ripple into service and industrial robotics.
Robots playing tennis are moving from demonstrations to real competition. According to a report by QbitAI, in a showdown being called the "AstraTennis moment," a robot faced a human tennis player for the first time, pulling off extreme ball saves and springing back up instantly after falling.
The report says it is the first publicly staged contest in which a robot took on a tennis athlete. Against real shots from the human player, the robot demonstrated fast movement and desperate saves, and even when it fell, it recovered to its feet in an instant to continue play.
Those moves look simple but demand sophisticated motion control: the robot must read the incoming ball's trajectory, plan its body posture in a fraction of a second, and keep its balance while swinging to strike.
The "instant recovery" after a fall is an even tougher test of joint actuation and dynamic balance algorithms — the robot has to detect the fall and return to a standing posture at full speed without breaking the flow of the match.
Moving from fixed lab routines to unpredictable shots on a real court, the contest shows how far embodied intelligence has come in dynamic environments, and offers a reference for applying robots in sports, services, and beyond.
What to watch next: whether human-versus-robot matches become a regular fixture, whether the robot can handle more varied shot patterns, and whether the underlying technology migrates to other athletic scenarios.
Why it matters
The human-versus-robot tennis match marks a leap for embodied intelligence in dynamic, high-speed settings, and its motion control and fast-recovery techniques could spill over into service and industrial robotics.
Nearby Updates
All08/23, 17:51
NVIDIA AI Servers to Rise 15% or More as Memory Costs Surge, Adding Up to $5B per 1GW Data Center
NVIDIA has told some of its biggest customers that AI servers delivered in early 2027 could cost 15% or more, with some GB300 and Vera Rubin 200 systems reportedly rising about 17%. A 1GW AI data center could see at least $5 billion in added costs as surging memory prices squeeze GPU supply chains.
08/23, 17:56
Anonymous LLM "Niulai" Traced to Zhipu Lineage; Cursor-GLM Speculation Grows
An anonymously released large language model called "Niulai" has been traced back to Chinese AI firm Zhipu, with analysts citing telltale signs in its tokenizer, video encoding, and API error messages. Separately, speculation is growing that Cursor may have trained on the open-source GLM models, though no direct evidence has emerged.
08/23, 17:58
让AI Agent「试玩」世界模型,长程目标评测有了新基准PlayWorld 手机新浪网
让AI Agent「试玩」世界模型,长程目标评测有了新基准PlayWorld 手机新浪网. 让AI Agent「试玩」世界模型,长程目标评测有了新基准PlayWorld 手机新浪网
08/23, 17:29
PhD-student founders bet on an all-in-one brain for bipedal humanoids as their robot drives a go-kart fully autonomously
A startup founded by several PhD students is betting on an integrated brain for bipedal humanoid robots instead of following Silicon Valley's playbook. In its latest demo, a robot drives a go-kart through consecutive corners fully autonomously in a single unedited take.