DexRobot Bridges AI Models and Real-World Dexterity at IROS 2026, Spotlighting DexGEM Milestone and Flagship DexHand021 Pro

PITTSBURGH, Sept. 30, 2026 /PRNewswire/ -- DexRobot, a full-stack embodied AI company focused on dexterous manipulation, is showcasing its complete dexterous manipulation capabilities at IROS 2026 (Booth 507), including three accepted research papers; the flagship DexHand021 Pro with full-palm multimodal sensing; and DexGEM, a phased research milestone of its in-house models demonstrating a technical closed loop in dexterous manipulation physical AI.

DexGEM: A Research Milestone in Physical AI Dexterity

DexGEM is the platform behind one of three accepted papers: "Dexterous Robot Manipulation from Human Demonstrations via Contact-Anchored Retargeting and Residual Policy Learning."

DexGEM learns dexterity from human hands. Demonstrations captured through motion capture and first-person video are reconstructed in simulation, adapted to robotic hands, and transferred to real robots, including exploration across different hand designs. Tasks run fully autonomously, with no teleoperation and no real-robot training data, spanning two-hand coordination such as object handovers and continuous-contact manipulation.

These results are built on DexRobot's dexterous hardware (DexHand021 series), native perception, and manipulation datasets accumulated over years, trained through in-house models and validated in real interaction scenarios.

DexHand021 Pro: Research-Grade Dexterity for Real-World Tasks

DexHand021 Pro combines 22 DoF in a wrist-hand integrated architecture with an actively driven 2-DoF wrist, enabling natural wrist-hand coordination for turning, aligning, flipping, and tool use. Its dual-tendon bidirectional drive with active distal joints enables independent active flexion and extension with precise force control and passive compliance.

Full-domain multimodal perception covers palm, fingertips, and finger sides: a 3D tactile envelope array offers 0.01 N normal-force resolution at 200 Hz sampling, while a 5-megapixel, 160° wide-angle palm camera tracks contact, force, and slip to guide adjustments.

A dedicated edge AI chip closes the perception-compute-control loop for millisecond-level decisions, with SDK, URDF, and development toolchains. Validated over 300,000+ durability test cycles with automotive-grade drive-and-control boards, the hand delivers the sensing, dexterity, and reliability that long-term embodied AI, robotics research, and high-dynamic tasks demand.

About DexRobot:

DexRobot integrates hardware, perception, data, models, and scenarios into a continuous pipeline: a complete dexterous hand portfolio; native multimodal perception; self-developed data acquisition and models that turn human demonstrations into training data and skills; and real-world scenarios validating every link, closing the loop from hardware to physical tasks, demonstrated by DexGEM on real robots.

For more information, please visit https://www.dex-robot.com/en or contact us at info@dex-robot.com.

** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **

DexRobot Bridges AI Models and Real-World Dexterity at IROS 2026, Spotlighting DexGEM Milestone and Flagship DexHand021 Pro

SUZHOU, China, Sept. 30, 2026 /PRNewswire/ -- A robotic hand developed by Chinese firm AGILINK has been taught foundational Suzhou embroidery techniques by master craftswoman Fu Xianghong, including separating silk threads, threading a needle, stretching fabric on an embroidery hoop and stitching.

The demonstration puts a robotic hand to work with one of the most delicate and deformable materials it can encounter: silk. A silk thread can bend, slip and change shape with slight changes in contact. Splitting silk requires one finger to separate individual strands while others maintain support and tension; twisting thread requires opposing fingertips to maintain contact while allowing the thread to turn. Threading a needle and stitching add further demands on positioning, force and coordination.

The OmniHand 3 Ultra combines 21 active degrees of freedom with a fully direct-drive architecture and tactile sensing across the fingertips, finger pads and palm. Vision-based tactile sensors at each fingertip detect changes in the contact surface, providing feedback as the hand handles thin, deformable materials.

"A single silk thread gives OmniHand 3 Ultra's fingertip dexterity a visible measure," said Qiao Tianjie, Vice President of AGIBOT and CEO of AGILINK. "It also reveals the possibility of handing more delicate work to machines."

The demonstration comes as AGILINK reaches a new stage of commercial scale. Spun out from AGIBOT in January 2026, the company has shipped more than 15,000 dexterous hands to date. In August, its OmniHand series competed across all eight dexterous-hand events at the World Humanoid Robot Games, winning seven gold, four silver and three bronze medals.

AGILINK reached unicorn status five months after launch, backed by investors including Hillhouse Ventures and Mirae Asset. Its fourth funding round in June valued the company at more than US$1 billion. The company sees dexterous manipulation of flexible and delicate materials as relevant to applications including cable handling, flexible-material assembly and precision-component manipulation.

"We'll have another pair of hands for delicate work," Fu said.

About AGILINK

AGILINK specializes in dexterous robotic manipulation, combining dexterous hardware, tactile sensing and control for delicate and deformable objects.

Watch the film: [https://youtu.be/uRy589aDp48]

** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **

Chinese robot hand learns Suzhou embroidery as AGILINK surpasses 15,000 dexterous hands shipped

Chinese robot hand learns Suzhou embroidery as AGILINK surpasses 15,000 dexterous hands shipped