BEIJING, Sept 10 (Reuters) – A week after his humanoid robot outran the world’s fastest man, Jack Guo is already chasing a tougher target: making machines that can work reliably in the real world.
TianGong Ultra stunned spectators at the World Humanoid Robot Games by running 100 metres in 8.64 seconds, almost a second faster than Usain Bolt’s world record. Behind the feat were days of round-the-clock testing and repairs as engineers pushed battered robots to their limits between races.
“When it started smoothly and got past 50 metres, that was when I finally relaxed,” said Guo, who leads development of Ultra and Omni, a smaller model used in 400m races, at the Beijing Humanoid Robot Innovation Centre, known as X-Humanoid.
Just a week later, the 34-year-old engineer has turned his attention to what he sees as a bigger challenge.
“We want to turn high performance into high reliability and high usability,” Guo told Reuters in his first interview with foreign media.
Ultra’s record-breaking run offers a glimpse of China’s rapid progress in humanoid robotics, where state-backed research, extensive supply chains and intense competition are driving advances in machine mobility.
But Guo’s next goal highlights the industry’s harder task: turning spectacular demonstrations into machines capable of performing useful jobs.
INSIDE THE WORKSHOP
X-Humanoid is based in Yizhuang, a high-tech development zone in southeast Beijing that has become one of China’s main robotics clusters. The area, long home to automakers, now features a robot sales centre and a robot-themed restaurant as part of the capital’s push to showcase the sector.
The company’s first-floor showroom displays generations of TianGong robots, including one still wearing the vest from a winning half-marathon run last year.
On the ninth floor, white Ultra and Omni humanoids stand suspended in metal frames. One wears a red “Champion TianGong” headband.
During a Reuters visit, engineers repaired and tested robots, with one removing a head cover, another tightening a leg and others conducting walking trials.
In an adjoining office, Guo’s team develops software before testing it on physical machines.
Founded in November 2023, X-Humanoid is backed by state-owned and private investors including robotics company UBTech, as well as Chinese technology giants Xiaomi and Baidu. It develops hardware, motion-control software and artificial intelligence for the wider industry while also commercialising its own robots.
The company has not disclosed how many of its robots it has sold or deployed commercially.
Its customers include universities, research institutes and companies exploring industrial applications. At Foton Cummins’ engine factory in Beijing, X-Humanoid robots have been trialled moving boxes, with its Tianyi 2.0 lifting 8-12 kg boxes onto shelves as part of what the factory described as an early-stage exploration.
USEFUL WORK BEGINS
Ultra was not originally designed to win races. It began as an experiment aimed at pushing the limits of humanoid movement.
Guo compares today’s humanoids with the earliest automobiles: first making them controllable, then combining reliable mechanical systems with increasingly capable AI “brains” that can handle complex tasks autonomously.
For now, he said, the priority is making the robot body and motion-control system stable enough for everyday use. Developing AI capable of handling more complicated autonomous tasks will take longer.
Running also helps develop more general mobility, improving a robot’s ability to cope with different terrain.
The smaller Omni has already demonstrated that capability in an internal test this year, climbing from the first floor to the 17th floor of X-Humanoid’s headquarters.
Guo expects smaller humanoids to find early applications in commercial services and light industry, while Ultra could eventually be used for outdoor inspections or emergency rescue.
One major challenge is braking. Ultra weighs 75 kg and can exceed 17 metres per second at top speed. At the Games, a crash mat was placed beyond a short run-off area, leaving sprinting robots to slam into a barrier after their 100-metre races.
Future versions could be lighter, brake more effectively and adopt safer running postures, Guo said.
CONQUERING SPEED
Ultra arrived at the Games with three running strategies trained in simulation. One had been battle-tested, while two were theoretically faster but less proven.
Each strategy is a trained motion-control system that continually adjusts the robot’s joints and balance, allowing it to sprint upright without an operator directing every movement.
Ultra used a different programme in each race, clocking 9.39 seconds in the preliminary round, 8.86 in the semi-final and 8.64 in the final.
Between races, engineers returned to their test site to push faster programmes and adjust navigation and running controls. Several worked through the night, sometimes testing into the following day before returning to the venue.
As the robots were pushed to their limits, some stumbled, lost balance or crashed, forcing teams to deploy backup machines while repair crews worked to restore damaged robots.
Earlier in development, the failures were even more severe.
“Legs broke, waists broke,” Guo said.
A LATE SURGE
Even on the morning of the final, Guo’s team was testing a newly trained running programme. It worked repeatedly in trials but failed on the competition track, while differences between individual robots created additional problems.
Ultra’s heavier legs limited its acceleration early in the race, but once it exceeded about 10 metres per second, it could continue building speed and reel in its rivals.
The team had cut roughly half a second from its starting response by the semi-final, Guo estimated. From there, the focus shifted to outright speed.
In the final, a faster reaction and stronger late acceleration helped Ultra pull away decisively.
Backstage, the team celebrated. At the closing ceremony, a row of TianGong humanoids wore red capes emblazoned with “Champion”, with some waving pom-poms.
“Finally, I could get a good night’s sleep,” Guo said.
