AI-powered robot runs like a human and breaks word record in China marathon race

AI News


If you think AI is all about intelligence and not muscle, think again. An AI-powered robot just ran a half marathon in China, and the results show that machines aren’t ready to beat humans in track and field. In a 21-kilometre race in Beijing, many humanoid robots not only completed the race, but some even completed it in less than an hour, leaving humans stuck around them forever.

The race saw more than 100 humanoid robots run along a 21.1-kilometre course alongside human participants. Although both groups ran the same route, organizers separated them with a barrier, creating a controlled comparison of speed, balance, and stamina.

And the humanoid robot was the first to cross the finish line, defeating its human competitors by an overwhelming margin.

The standout performance came from a robot developed by Chinese smartphone maker Honor, which finished the race in 50 minutes and 26 seconds. According to Reuters, this was significantly faster than the fastest human runner, who finished in 1 hour, 7 minutes, 47 seconds. In theory, the robot’s time could also beat the current world record for a human half marathon, but experts caution that such comparisons are not strictly apples-to-apples.

The robot’s win marks a major comeback for the machines from last year’s race, when they struggled to finish with several robots losing their balance or requiring assistance. This time, many machines maintained their pace and completed the race with little trouble. The report said the event highlighted how rapidly technology is evolving.

A significant number of robots demonstrated improved balance, coordination, and endurance compared to previous attempts.

Around 40 percent of the robots in the race were reportedly fully autonomous, relying on onboard sensors and AI systems to navigate the course, maintain balance, and adjust their stride length in real time. Time penalties were imposed on remotely controlled robots, and additional penalties were applied for battery changes or complete replacements during the race.

However, the machine is still far from perfect. Even the best-performing robots struggled with the limitations of the technology. He briefly clipped the railing a few meters before the finish line, but it was a small reminder that his precision and consistency still needed improvement.

Engineers say many of these humanoid advances are due to designing robots that more closely mimic human movements. Du Xiaodi, an engineer on the Honor team, told Reuters that the structure of the robot’s legs (90 to 95 centimeters long) is optimized for stride efficiency, similar to that of elite runners. The system also uses liquid cooling technology to prevent overheating during long workouts.

Spectators of the human-versus-machine race noticed a visible improvement in the robot’s movements. Many had a running style that more closely resembled human movement and appeared more stable and fluid. For some, the race also offered a glimpse into future career paths. Chu Tianqi, a 23-year-old engineering student, told Reuters that the robot’s performance reflected the rapid pace of AI development and that younger participants were showing interest in researching robotics.

Experts say that even though the robots are impressive, the results should be seen in context. Running a race, even over long distances, is a controlled task compared to real-life environments. They point out that for now, humanoid robots still face challenges in areas such as fine motor skills, adaptability, and decision-making in unpredictable situations.

– end

Publisher:

Divya Bhati

Publication date:

April 19, 2026 12:43 IST

Please tune in



Source link