SHANGHAI, Dec. 22, 2025 /PRNewswire/ — TARS Robotics, an AI-driven embodied intelligence company, made a historic debut by demonstrating a humanoid robot capable of performing hand embroidery. During a live event, the robot executed the delicate, long-sequence task of threading a needle and stitching a logo with both hands. This feat demands sub-millimeter precision, adaptive force control, and coordinated bimanual manipulation of flexible materials—a combination that has remained an unsolved challenge in embodied intelligence until now. This breakthrough in ultra-fine, flexible manipulation effectively overcomes a major industrial automation barrier, enabling robots to perform similarly complex tasks like intricate wire harness assembly and providing a new pathway for intelligent manufacturing upgrades.
jwplayer.key=”3Fznr2BGJZtpwZmA+81lm048ks6+0NjLXyDdsO2YkfE=” jwplayer(‘myplayer1’).setup({file: ‘https://mma.prnasia.com/media2/2850516/final1219.mp4’, image: ‘https://mma.prnasia.com/media2/2850516/final1219.mp4?p=medium’, autostart:’false’, stretching : ‘uniform’, width: ‘512’, height: ‘288’});
At the event, Dr. Chen Yilun, CEO of TARS, revealed that the key to crossing this technological boundary—long deemed "impossible to automate"—lies in a systematic DATA-AI-PHYSICS trinity solution. TARS’s human-centric SenseHub system captures rich, real-world operational data, which fuels the TARS AWE (AI World Engine) 2.0. This embodied AI model learns generalizable skills for precise physical control, capabilities that are fully realized on TARS’s T- and A-Series robots. Engineered with a "minimal digital-to-physical gap," these robots translate AI capabilities into stable actions in the physical world.
Dr. Chen added that TARS has thereby established a complete technological closed loop—from real-world data generation and intelligent decision-making to physical execution. This provides a replicable, scalable engineering pathway for embodied intelligence to enter real-world production and daily life, one that aligns with Scaling Law.
Dr. Ding Wenchao, Chief Scientist of TARS, stated: "Leveraging the massive data from SenseHub and guided by the AWE 2.0 model, we have seen a leap forward in task success rates across multiple scenarios. As we continue to scale our data and advance our model architecture, we foresee new breakthroughs in our robots’ intelligence and generalization capabilities, with the ultimate goal of deploying them across every industry and household."
Since its founding on February 5, 2025, TARS has—in less than a year—successfully deployed its core algorithms in practical applications and achieved continuous performance upgrades for its advanced robotic platforms. The company is driven by its mission to build trusted AI robotics solution and is backed by strong investor support, including a $120 million Angel Round from investors such as Lanchi Ventures and a subsequent $122 million Angel+ Round.
This content was prepared by our news partner, Cision PR Newswire. The opinions and the content published on this page are the author’s own and do not necessarily reflect the views of Siam News Network
