MIT researchers channel AI to turn hand gestures into robot training data - Greenwich Time
Subscribe Living # MIT researchers channel AI to turn hand gestures into robot training data By RODRIQUE NGOWI, Associated PressUpdated CAMBRIDGE, Mass.
Key takeaways
The most recent developments show a rapid shift from prototype demonstrations toward large‑scale manufacturing and commercial deployment of humanoid robots. In China, Lingyi iTech’s new Beijing factory has already built 300 units and is targeting 10,000 this year, with a long‑term goal of 500,000 annually by 2030, a scale that could cut the typical $30,000 price tag dramatically. Meanwhile, the Chinese market shipped more than 13,000 humanoids in 2025, and analysts expect sales to more than double to around 28,000 units in 2026, with a possible million‑unit annual volume by the early 2030s, although demand still trails production capacity. Outside China, Standard Bots secured a $200 million Series C round that lifted its valuation to $1 billion, underscoring investor confidence in mass‑producing humanoids. Figure AI announced an accelerated manufacturing line and a logistics partnership with Catalyst Brands to field its humanoid platforms in distribution centers. On the technology front, Sharpa integrated its Wave tactile robot hands into Unitree’s H2 Plus humanoid reference design, creating the first dexterous humanoid built on Nvidia’s Isaac GR00T framework. This move highlights a broader industry emphasis on manipulation and tactile sensing rather than just locomotion. In Europe, the UK‑based company Humanoid sealed a proof‑of‑concept partnership with Bosch, positioning the venture for scaled production, while Agile Robots unveiled its AgileONE humanoid and a suite of force‑control systems at the Robot Technology Japan event, demonstrating advanced embodied AI and collaborative capabilities. Academic research is also progressing: MIT researchers introduced a wearable ultrasound wristband that captures fine hand‑muscle movements in real time, providing a new source of training data that could help future humanoids achieve human‑level dexterity. Overall, the sector is moving quickly toward higher production volumes, lower costs, and more sophisticated manipulation, even as analysts caution that finding enough real‑world buyers remains a critical challenge.
Subscribe
Living
MIT researchers channel AI to turn hand gestures into robot training data
By RODRIQUE NGOWI, Associated PressUpdated
CAMBRIDGE, Mass. (AP) — Humanoid robots struggling with tasks like grasping a cup have a new teacher — a person wearing an ultrasound wristband that captures the movement of muscles, tendons and ligaments beneath the skin.
Researchers at the Massachusetts Institute of Technology developed the tool to collect data of human hand motion that could eventually help robots achieve the dexterity that has been difficult for machines to master.
Article continues below this ad
Article continues below this ad
In laboratory demonstrations with eight volunteers, developers showed the wristband could precisely mirror hand gestures – including all 26 letters in American Sign Language – within 120 milliseconds.
The wristband can operate wirelessly, meaning the controlling person and the receiving robot need not be in the same room.
Beyond remote control, the team sees a path toward using the wristband to build huge datasets of human motion that could eventually enable humanoids to learn dexterous tasks without human guidance.
Article continues below this ad
___
AP Technology Writer Matt O'Brien contributed to this report.
|Updated
RODRIQUE NGOWI
Most Popular
Mentioned in this article