惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
月光博客
月光博客
爱范儿
爱范儿
The Cloudflare Blog
Y
Y Combinator Blog
B
Blog RSS Feed
Stack Overflow Blog
Stack Overflow Blog
博客园 - 叶小钗
G
Google Developers Blog
J
Java Code Geeks
P
Proofpoint News Feed
美团技术团队
Engineering at Meta
Engineering at Meta
腾讯CDC
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
博客园_首页
WordPress大学
WordPress大学
博客园 - 聂微东
雷峰网
雷峰网
有赞技术团队
有赞技术团队
L
LangChain Blog
N
Netflix TechBlog - Medium
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
博客园 - 【当耐特】

Interesting Engineering

US firm to scale laser-based nuclear fusion ‘breakthrough’ with new partnership Military Archives - Interesting Engineering World’s first non-nuclear lead-cooled reactor to generate electricity begins installation US scientists devise new process to turn sewage sludge into 99% pure natural gas US firm unveils submarine-hunting drone with 9,200-mile-range, 35 mph top speed Military Archives - Interesting Engineering Supercomputer finds lithium-titanium tweak to boost sodium-ion batteries for grids Lockheed Martin demonstrates vertical launch missile system for mobile drone defense China’s 1116 MWe Taipingling Unit 1 reactor goes online, set to generate 9bn kWh yearly ChatGPT Images 2.0 update combines reasoning, research, and design with 2K output US Navy tests plug-and-play laser system on USS Bush carrier, downs drones at sea China’s CATL reveals 621-mile EV battery, under-7-minute charging to challenge BYD US uses world’s first exascale supercomputer to model supernovae, fusion reactors AI and Robotics Archives - Interesting Engineering First-in-human study confirms safety of graphene-based brain interface Tesla’s Optimus humanoid robot greets runners, poses for photos at Boston Marathon Interlocking materials offer high strength and flexibility for robotics, infrastructure US redeploys 100,000-ton nuclear-powered aircraft carrier in Red Sea after repairs US scientists unveil concept for ‘world’s first neutrino laser’ to unlock breakthroughs New military tech can maintain communication in contested electronic warfare environments Got a dark personality? Psychologists can help you choose your career wisely Humidity boosts performance of 3D-printed nanogenerator instead of degrading it China demonstrates microwave beam that recharges drones in flight, continues power delivery Scientists run compact free-electron laser for eight hours, cracks FEL stability problem China’s PLA considers to use minelaying underwater drones to enforce Taiwan blockade: Report 1-ton sharks may struggle for survival in waters exceeding 62.6°F, study suggests US firm’s thorium nuclear fuel bundles move to manufacturing for commercial reactors Tesla hits 0% charge in remote Chilean desert as YouTuber uses hood-mounted solar Humanoid robot surpasses human world record in Beijing half-marathon, clocking 50:26 mins New method extracts maximum work from unknown quantum states using symmetry tricks
China’s new robotic hand combines hybrid actuation for sm...
Jijo Malayil · 2026-05-21 · via Interesting Engineering

Chinese robotics firm Xynova has unveiled its second-generation dexterous hand, aiming to improve humanoid robots’ ability to perform human-like manipulation tasks in real-world environments.

The new Gen-2 hand, named Flex 2, combines multiple actuation technologies in a hybrid drive system, enabling it to handle objects with different shapes, textures, and levels of fragility more effectively.

Designed to move beyond the limitations of rigid industrial grippers, the robotic hand can adapt to delicate and irregular objects with greater precision and flexibility.

Xynova says the technology is intended to advance humanoid robots toward more intelligent and versatile task execution across industries.

Humanlike grasp evolution

The robotic hand features a 23-degree-of-freedom bionic design engineered for fast, human-like movement and precise manipulation.

Weighing just 0.88 pounds (400 grams), the hand can perform two fist extensions per second, delivering agile and responsive motion similar to a human hand. It also achieved a perfect score in the Kapandji Thumb Opposition Test, demonstrating strong dexterity and shape adaptation capabilities, according to the firm’s website.

Designed for precision tasks, Xynova claims the system offers repeatability of ±0.1 millimeters and supports hybrid force and position control through back-drivable actuation under load. Its force control accuracy reaches as low as 0.05 newtons, enabling delicate object handling.

The hand integrates multi-modal perception, tactile sensing, and a human-like “cerebellum” system for adaptive grasping, slip detection, and compliant reflexes. An open development ecosystem also allows developers to customize and expand its capabilities.

In terms of strength, the robotic hand can support a single-hand grasp load of 26.4 pounds (12 kilograms) and a continuous operation load of 8.8 pounds (4 kilograms). Wear-resistant surfaces and micro linear actuators provide durable yet powerful performance.

The system is also built for reliability, offering resistance to dust, drops, and impacts while supporting millions of operation cycles across demanding environments.

Advanced hybrid manipulation

Flex 2 represents Xynova’s latest step toward building dexterous robotic hands capable of human-like manipulation in real-world environments.

The hybrid-drive system combines cable-driven tendons with direct-drive actuation, balancing flexibility, compactness, and precision in a way that mirrors the mechanics of the human hand. Tendon-driven systems provide compliance and lightweight movement, while direct-drive actuation delivers the torque and control needed for accurate object handling during complex tasks.

The company’s earlier Flex 1 model already demonstrated strong hardware performance with 25 degrees of freedom, a 380-gram weight, 66 pounds (30 kilograms) load capacity, and 20-newton fingertip force. With Flex 2, the focus shifts toward improving control fidelity during physical interaction, an area that remains one of the biggest challenges for robotic hands operating outside controlled environments.

Xynova has also redesigned the vision system by moving the camera from the palm to the wrist joint. The change helps maintain a clear visual stream while grasping objects, avoiding the occlusion problems common in palm-mounted designs. This could significantly improve the quality of data collected for vision-language-action training pipelines used in embodied AI systems.

Combined with integrated tactile sensing and proprioception, the new sensor stack is aimed at solving the “last centimeter” challenge in robotics — enabling humanoid robots to perform precise, contact-rich manipulation tasks with greater reliability and adaptability.

The Blueprint

Get the latest in engineering, tech, space & science - delivered daily to your inbox.

Jijo is an automotive and business journalist based in India. Armed with a BA in History (Honors) from St. Stephen's College, Delhi University, and a PG diploma in Journalism from the Indian Institute of Mass Communication, Delhi, he has worked for news agencies, national newspapers, and automotive magazines. In his spare time, he likes to go off-roading, engage in political discourse, travel, and teach languages.