Humanoid robots have broken records in sprinting and other sports, but they struggle to hammer nails.
The first humanoid robot ran faster than a human, the second jumped over 3 meters high, breaking a record, and the third competed against a human Olympic champion in a table tennis demonstration match, all of which were impressive performances at the 2nd World Humanoid Robot Sports Competition recently held in Beijing, an event aimed at challenging the physical limits of robots.
The robotics competition intuitively showcased the rapid iteration of humanoid robots - humanoid robots using AI to learn, plan and execute real-world actions. But we also saw that these robots still have a long way to go in helping humans cope with actual tasks.
"If I ask you which action is more difficult - folding clothes or doing a backflip, most people would definitely say folding clothes is simple," said Karen Liu, a computer scientist at Stanford University in California, "but for humanoid robots, the tasks we do every day are much more difficult than a backflip."
This year's competition, which took place from August 22 to August 26, featured more than 600 teams, primarily from Chinese universities, research institutes, and robotics companies, with events expanding from track and field to real-world challenges such as sorting bookshelves and making beds. The scene contests preceded the athletic contests, in which robots that could complete tasks independently scored higher than those controlled remotely by humans in these "scenario-based tasks".
This sports event is more than just a competition—it's a critical field test for embodied intelligence, according to Cheng Hao, CEO of Beijing-based Accelerate Evolution Technology. The company sent nearly 300 robots to compete.
The Associated Press' video captures the on-site performance at the 2nd World Robot Games in Beijing and interviews some of the participating R&D teams. Source: Associated Press
The emphasis on practical tasks in competitions is too important for the development of practical robots, Aya Durbin said. Durbin, who led the development of the Atlas humanoid robot at Boston Dynamics in the US, did not send robots to compete. "If humanoid robots are just 'toys', they will never be able to participate in our daily lives. They must be able to solve real-life 'pain points' and make the world a better place."
Pros and Cons
A robot from Beijing-based X-Humanoid won a gold medal in the 100-meter dash with a time of 8.64 seconds - nearly a second faster than Usain Bolt's world record in 2009. The robot won the 100-meter dash with a time of 21.5 seconds last year, demonstrating the rapid development of the technology. Another X-Humanoid robot set a new record for a vertical jump from a standing position, reaching 3.4 meters, breaking the human record set in 1993, according to the Global Times.
Humanoid robots excel on the track because they are extremely efficient at converting energy into acceleration, Liu said. For robots, backflips and sprints are just a matter of following a predetermined trajectory, she said, "down to every thousandth of a second, the robot knows what to do and how much torque to produce - it doesn't need to 'think'."
In a video released by Chinese state media CCTV+, one competition tests robots' ability to hammer nails into a wooden board - with varying degrees of success. Source: CCTV+
What poses difficulties for humanoid robots are tasks that require high dexterity, Liu said, citing the challenge of developing "dexterous hands" or grippers that can mimic human hand strength and coordination, making it particularly hard for these robots to use tools due to the small contact surface of the dexterous hands, which makes it difficult to exert force.
Indeed, the robots on the field had a tough time hammering nails into the wooden board, even with team members wearing gloves to manipulate the robots' every move, and they couldn't guarantee a 100% success rate.
"Physical AI models" that can translate input data into real-world actions are accelerating the optimization and iteration of humanoid robots, Durbin said. Researchers train these models in several ways, including having humans wear virtual reality headsets and sensors to collect task-based data for robots to mimic, or having robots train in simulated scenarios before performing real-world tasks.
Task-Oriented Robots
Enhancing the ability of humanoid robots to perform actual "work" is crucial, as this is where they can be utilized, researchers told Nature. "The tasks you think 'I don't want to do' are the ones we want Atlas to do," Durbin said. These tasks can range from folding clothes to operating in high-risk environments, such as high-radiation environments, which are harmful to humans but not to robots. Cheng Hao said Beijing Acceleration Evolution Technology is also attempting to have humanoid robots handle repetitive, physically demanding, or flexible tasks.
However, to deeply integrate into the real world, humanoid robots are still too prone to errors, according to Durbin. Moreover, because they are heavy, if the system fails or they fall, they can easily cause harm, making them a danger when unmonitored, said Chris Atkeson, a robotics researcher at Carnegie Mellon University. Atkeson has long dreamed of designing lightweight, soft robots that can care for humans without causing harm. (His idea was the inspiration for Baymax, the assistive robot in the Disney movie Big Hero 6.) Durbin said that leaving robots at home is a dangerous scenario unless rules and standards are established, and robots should be designed to "touch down in the safest, most controlled way" rather than falling due to a malfunction.
These robots are currently pricey, so they won't be helping with household chores anytime soon. The most affordable humanoid robots on the market include a basic model sold by Hangzhou-based robotics company Unitree, priced at just under $5,000. More advanced models can cost over $100,000.
Of course, the competition was not entirely smooth sailing: some robots shattered upon crashing into walls, others tripped over themselves, and a few caught fire at the finish line. Still, the event served as an entertaining way to ease the public into accepting a new idea: that with continuous refinement, robots could gradually become part of everyday life. "Robots are meant to be fun," Durbin said.
The "Robot Olympics" revealed humanoids' rapid progress—and flaws, published on August 27, 2026, in the news section of Nature.
Nature