Connect with us

AI Research

Box, run, crash: China’s humanoid robot games show advances and limitations | China

Published

on


A quick left hook, a front kick to the chest, a few criss-cross jabs, and the crowd cheers. But it is not kickboxing prowess that concludes the match. It is an attempted roundhouse kick that squarely misses its target, sending the kickboxer from a top university team tumbling to the floor.

While traditional kickboxing comes with the risk of blood, sweat and serious head injuries, the competitors in Friday’s match at the inaugural World Humanoid Robot Games in Beijing faced a different set of challenges. Balance, battery life and a sense of philosophical purpose being among them.

The kickboxers, pint-sized humanoid robots entered by teams from leading Chinese technological universities, are part of a jamboree of humanoid events taking place at China’s latest technology event. After spectators in the 12,000-seater National Speed Skating Oval, built for the 2022 Winter Olympics, stood for the Chinese national anthem on Friday morning, the government-backed games began.

“I came here out of curiosity,” said Hong Yun, a 58-year-old retired engineer, sat in the front row. Seeing the robots race was “much more exciting than seeing real humans”, Hong added.

Robots compete in a five-a-side football match on the first day of the World Humanoid Robot Games in Beijing on Friday. Photograph: Tingshu Wang/Reuters

The games put on display China’s prowess in humanoid robotics, a technological field that has been pushed to the forefront of the country’s artificial intelligence industry. The hype machine is in full swing.

As well as kickboxing, humanoids participated in athletics, football and dance competitions. One robot had to drop out of the 1500-metre because its head flew off partway round the course. “Keeping [the head] balanced while in movement is the biggest challenge for us,” said Wang Ziyi, a 19-year-old student from Beijing Union University, who was part of the team that entered the robot.

Ever since a troupe of humanoid dancing robots took the stage at the 2025 Spring Festival Gala, a televised lunar new year’s celebration viewed nearly 17bn times online, Beijing has been enthusiastically pushing the adoption of “embodied AI” – an industry that was singled out in this year’s government work report in March.

One robot had to drop out of the 1500m partway because its head flew off. Photograph: Kevin Frayer/Getty Images

The social-media-friendly events reflect a more serious geopolitical reality: an intensifying US-China technological competition that could reshape the frontiers of AI.

The technology has become a lightning rod for relations between the two countries. And while the US still has the lead on frontier research, owing in part to Washington’s restrictions on the export of cutting-edge chips to China, Beijing is going all-in on real life applications, such as robotics.

Several cities, including Beijing and Shanghai, have established 10bn yuan (£1bn) robotics industry funds. In January, the state-owned Bank of China announced plans for a 1tn yuan of financial support to the AI industry over the next five years.

“If there is an area where [Beijing] thinks that China is ahead, or could be positioned as a world leader, then they really want to draw attention to that area,” said Dr Kyle Chan, a researcher at Princeton University.

A robot is carried off after a kickboxing match on the first day of the games. Photograph: China News Service/Getty Images

There is something strangely ominous about seeing jerky, human-like robots with two arms, two legs, and blank heads being dragged out of the ring to be recharged by their human handlers.

When it comes to humanoids, the Chinese industry has many advantages. Although US companies such as Tesla and Boston Dynamics are still seen as the overall market leaders, several Chinese firms such as UBTech and Unitree Robotics – which supplied the boxing robots in Friday’s games – are catching up.

Tesla relies on China for many of the parts needed to build the company’s physical humanoids. The US investment bank Morgan Stanley estimates that China-based supply chains produce robots at a third of the cost of non-China suppliers. “It appears to be very difficult to entirely decouple from China in this space,” wrote Sheng Zhong, the bank’s head of China industrials research, in a recent note.

A robot built by the Chinese company Unitree Robotics plays a traditional drum. Photograph: Tingshu Wang/Reuters

As well as generating positive publicity on social media, China views humanoids as being part of the solution to the problems created by the country’s ageing population and shrinking workforce. A recent article in People’s Daily, a mouthpiece of the Chinese Communist party, said robots could offer practical and emotional support for older people. “The vision of robot-assisted elderly care is not far away,” it said. Humanoid robots could also take the place of employees on factory lines as China tries to retrain and redeploy its workforce into more hi-tech jobs.

But for all the hype, there is a big gap between humanoids stumbling over footballs and reliably handling daily tasks. Safely interacting with vulnerable humans would be another leap. “The home is probably one of the last places you’ll ever find a humanoid robot because of safety,” said Chan. “My general view on the whole humanoid explosion … is honestly a bit of scepticism.”

A technician works on humanoid robots on the sidelines of the games. Photograph: Kevin Frayer/Getty Images

Two of the biggest barriers to the technology being useful outside of PR stunts are the complexity of the human-built environment and the hands needed to navigate it.

While other forms of AI, such as large language models, can be trained using reams of digital data, there are much smaller datasets available for training an algorithm on how to walk through crowded restaurants or up and down flights of stairs. Although China’s efforts to get robots out into the real world can help companies to harvest more data, it is still a big bottleneck in the industry, Chan said.

Dr Jonathan Aitken, a robotics teacher at the University of Sheffield, agreed. “The state of AI is nowhere near seeing humanoids operating out of uncontrolled environments,” he said.

And while robots jumping and kicking looks impressive, mundane daily tasks such as handling a kitchen knife or folding laundry requires dexterous hands, a skill technology companies have yet to crack. A human hand has about 27 “degrees of freedom” – ie, independent movements through space. Tesla’s Optimus humanoid, one of the most advanced models on the market, has 22.

Still, China has beat the odds before when it comes to turbocharged advances. Just 10 years ago, the country exported fewer than 375,000 cars a year. Now China is the world’s biggest automobile supplier, shipping nearly 6m vehicles annually. The European Union has increased tariffs on Chinese-built electric vehicles in an attempt to stem the flow.

In China, the political and public will is firmly behind the humanoids. Zhan Guangtao came to the humanoid games with her two daughters on Friday, after her elder child’s school gave them free tickets. “It’s good to have my children in touch with the world’s most advanced robotics,” Zhan said. “Exposing them to hi-tech will broaden their horizons.”

Additional research by Lillian Yang



Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

AI Research

How artificial intelligence is transforming hospitals

Published

on


Story highlights

AI is changing healthcare. From faster X-ray reports to early warnings for sepsis, new tools are helping doctors diagnose quicker and more accurately. What the future holds for ethical and safe use of AI in hospitals is worth watching. Know more below.



Source link

Continue Reading

AI Research

AI is becoming the new travel agent for younger generations, survey finds

Published

on


Is travel planning the next space AI is taking over?

A new survey shows that younger Americans are relying on AI and ChatGPT more and more to construct their vacation itineraries.

The survey of 2,000 Americans (split evenly by generation) by Talker Research found that only 29% of millennials have never used AI for this reason, with just 33% of Gen Z saying the same.

This is a stark contrast to older generations that still rely on old-school, traditional methods to sort their travel plans. Seven in ten baby boomers also say they have never used AI for their travel plans.

IN CASE YOU MISSED IT | Travel cutbacks: Americans planning shorter, more frequent trips this summer

So exactly how are people utilizing AI in this way? The interesting results emerged in Talker Research’s new travel trend report.

The top application for AI in travel planning was found to be asking it to compare flight prices for wherever they’re headed, with 29% of all those polled saying they’ve done this.

A similar amount says AI comes in even before that: Twenty-nine percent of respondents have even asked it where they should go for their trip.

Another one in five even let AI complete a detailed plan for their whole trip, complete with sights to see, local things to do and museums to tick off.

While word of mouth and recommendations from loved ones have always been the most common way to learn about fun places to travel, the survey revealed that there’s a new contender.

YouTube (34%) was crowned as the top resource people use for travel inspo, officially topping recommendations from family (30%) and friends (28%).

The generations were split on this, as unsurprisingly, younger generations were a lot more reliant on social media than older generations.

FROM THE ARCHIVES | Affordable travel destinations that can save you thousands of dollars

While YouTube was the most popular when accounting for every survey-taker, Gen Z was overwhelmingly using TikTok for travel inspiration (52%).

In comparison, just 27% of millennials and only 2% of boomers said they use TikTok for this purpose.

While AI is still fairly new, it’s easy to see this trend growing as the technology becomes more sophisticated.

Survey methodology:

This random double-opt-in survey of 2,000 Americans (500 Gen Z, 500 millennials, 500 Gen X, 500 baby boomers) was conducted between May 5 and May 8, 2025 by market research company Talker Research, whose team members are members of the Market Research Society (MRS) and the European Society for Opinion and Marketing Research (ESOMAR).





Source link

Continue Reading

AI Research

If I Could Only Buy 1 Artificial Intelligence (AI) Chip Stock Over The Next 10 Years, This Would Be It (Hint: It’s Not Nvidia)

Published

on


While Nvidia continues to capture headlines, a critical enabler of the artificial intelligence (AI) infrastructure boom may be better positioned for long-term gains.

When investors debate the future of the artificial intelligence (AI) trade, the conversation generally finds its way back to the usual suspects: Nvidia, Advanced Micro Devices, and cloud hyperscalers like Microsoft, Amazon, and Alphabet.

Each of these companies is racing to design GPUs or develop custom accelerators in-house. But behind this hardware, there’s a company that benefits no matter which chip brand comes out ahead: Taiwan Semiconductor Manufacturing (TSM -3.05%).

Let’s unpack why Taiwan Semi is my top AI chip stock over the next 10 years, and assess whether now is an opportune time to scoop up some shares.

Agnostic to the winner, leveraged to the trend

As the world’s leading semiconductor foundry, TSMC manufactures chips for nearly every major AI developer — from Nvidia and AMD to Amazon’s custom silicon initiatives, dubbed Trainium and Inferentia.

Unlike many of its peers in the chip space that rely on new product cycles to spur demand, Taiwan Semi’s business model is fundamentally agnostic. Whether demand is allocated toward GPUs, accelerators, or specialized cloud silicon, all roads lead back to TSMC’s fabrication capabilities.

With nearly 70% market share in the global foundry space, Taiwan Semi’s dominance is hard to ignore. Such a commanding lead over the competition provides the company with unmatched structural demand visibility — a trend that appears to be accelerating as AI infrastructure spend remains on the rise.

Image source: Getty Images.

Scaling with more sophisticated AI applications

At the moment, AI development is still concentrated on training and refining large language models (LLMs) and embedding them into downstream software applications.

The next wave of AI will expand into far more diverse and demanding use cases — autonomous systems, robotics, and quantum computing remain in their infancy. At scale, these workloads will place greater demands on silicon than today’s chips can support.

Meeting these demands doesn’t simply require additional investments in chips. Rather, it requires chips engineered for new levels of efficiency, performance, and power management. This is where TSMC’s competitive advantages begin to compound.

With each successive generation of process technology, the company has a unique opportunity to widen the performance gap between itself and rivals like Samsung or Intel.

Since Taiwan Semi already has such a large footprint in the foundry landscape, next-generation design complexities give the company a chance to further lock in deeper, stickier customer relationships.

TSMC’s valuation and the case for expansion

Taiwan Semi may trade at a forward price-to-earnings (P/E) ratio of 24, but dismissing the stock as “expensive” overlooks the company’s extraordinary positioning in the AI realm. To me, the company’s valuation reflects a robust growth outlook, improving earnings prospects, and a declining risk premium.

TSM PE Ratio (Forward) Chart

TSM PE Ratio (Forward) data by YCharts

Unlike many of its semiconductor peers, which are vulnerable to cyclicality headwinds, TSMC has become an indispensable utility for many of the world’s largest AI developers, evolving into one of the backbones of the ongoing infrastructure boom.

The scale of investment behind current AI infrastructure is jaw-dropping. Hyperscalers are investing staggering sums to expand and modernize data centers, and at the heart of each new buildout is an unrelenting demand for more chips. Moreover, each of these companies is exploring more advanced use cases that will, at some point, require next-generation processing capabilities.

These dynamics position Taiwan Semi at the crossroad of immediate growth and enduring long-term expansion, as AI infrastructure swiftly evolves from a constant driver of growth today into a multidecade secular theme.

TSMC’s manufacturing dominance ensures that its services will continue to witness robust demand for years to come. For this reason, I think Taiwan Semi is positioned to experience further valuation expansion over the next decade as the infrastructure chapter of the AI story continues to unfold.

While there are many great opportunities in the chip space, TSMC stands alone. I see it as perhaps the most unique, durable semiconductor stock to own amid a volatile technology landscape over the next several years.

Adam Spatacco has positions in Alphabet, Amazon, Microsoft, and Nvidia. The Motley Fool has positions in and recommends Advanced Micro Devices, Alphabet, Amazon, Intel, Microsoft, Nvidia, and Taiwan Semiconductor Manufacturing. The Motley Fool recommends the following options: long January 2026 $395 calls on Microsoft, short August 2025 $24 calls on Intel, short January 2026 $405 calls on Microsoft, and short November 2025 $21 puts on Intel. The Motley Fool has a disclosure policy.



Source link

Continue Reading

Trending