Latest From Shadow: Shadow Hand & Glove For Dexterous Manipulation read about it here.

Dexterous Hand Series

The World’s Most Dexterous Humanoid Robot Hand Helping the Advances in Robotic Research.

shadow dexterous hand - able to handle objects designed for humans
shadow dexterous hand - holding an wooden ball

uses and benefits

A trusted favourite among universities and companies.

It is used as a research and development tool (fully ROS integrated) and as a testing hardware for AI and Machine Learning.

Our robot hands are also a key component in our Shadow Teleoperation System - the world’s most advanced teleoperation technology.

If you see the Dexterous Hand fitting in with your work or if you would like to request a demo, get in touch.

Contact us
dexterous hand series - flagship img.png

ANTHROPOMORPHIC CHARACTERISTICS: The presence of nails and flesh provides the robot with high-friction and deformable materials for better grasping and manipulation.

The ONLY robot hand on the market to have 24 movements and 20 degrees of freedom (DOF) for increased flexibility in grasping and manipulating a range of objects.

The positioning of the fingers and the knuckles give comparable fingertip locations to the human hand.

All hands come with standard touch sensing at the fingertips. A single region sensor is used with a range of 0.1N to 25N. You can upgrade to have sensors that also measure temperature and vibration.

Includes the flex of the palm for the little finger and finger nails for the closest kinematics to the human hand, making it familiar to deploy and intuitive to handle.

With 2 extra DOF at the wrist, it provides flexibility, optimises accurate positioning of the hand, and helps avoid singularities when mounted on a robot arm.

We also have load gauges close to the actuator that give you information about the tendon tension.

 

We have Maxon motor actuators in the forearm for high quality performance.

Flagship product

Dexterous Hand

Our most advanced 5-fingered Dexterous Hand is used by researchers all over the globe.

our flagship product - dexterous hand, capable of in hand manipulation
Palm flex The extra DOF here allows the little finger to oppose the thumb and gives the palm more human-like behaviour.
Wrist
With 2 extra DOF at the wrist, it provides flexibility, optimises accurate positioning of the hand, and helps avoid singularities when mounted on a robot arm.

Abduct/Adduct
Each finger has an independent side-to-side motion for impressive in-hand manipulation and other movements with advanced dexterity

Tendon Driven
Provides postural stability, shock mitigation, and bending to facilitate dexterous motion.
Multiple tactile sensing options
A range of different finger tactile tips are available depending on your dexterity needs

Flagship product

Shadow Dexterous Hand

Our Shadow Dexterous Hand is the most advanced 5-fingered robotic hand available, and it's being used by researchers all over the world. It offers unprecedented accuracy and dexterity, allowing researchers to manipulate tools and objects with greater precision and control than ever before. . With this dexterous hand, researchers can explore new avenues of robotics and artificial intelligence, as well as refine existing technologies.

  • Compare Dexterous Hand Series
  • Specifications
  • Price List

Overview

Shadow Dexterous Hand

Shadow Dexterous Hand Lite

Shadow Dexterous Hand Extra Lite

Shadow Dexterous Hand Super Lite

Degrees of Freedom (DOF) 20 actuated DOF and a further 4 under-actuated movements for a total of 24 joints 13 DOF across 16 joints 10 DOF across 12 joints 7 DOF across 8 joints
Overall Weight 4.3 Kg 2.4 Kg 2.1 Kg 1.8 Kg
No. of Fingers 4 + 1 (thumb) 3 + 1 (thumb) 2 + 1 (thumb) 1 + 1 (thumb)
No. of Actuators 20 DC motors 13 DC motors 10 DC motors 7 DC motors
No. of Finger Joints 4 4 4 4
No. of Thumb Joints 5 4 4 4
No. of Wrist Joints 2 0 0 0
No. of Tip Pressure Sensors 5 4 3 2
No. Inertial Measurement Units (IMU) 1 1 1 1
No. of Tendon Load Sensors 40 26 20 14
Control loop rate through host 1Khz (EtherCat protocol) 1Khz (EtherCat protocol) 1Khz (EtherCat protocol) 1Khz (EtherCat protocol)
ROS Open Source Platform dexterous hand series - check list dexterous hand series - check list dexterous hand series - check list dexterous hand series - check list
Easily Integrated on Robot Arms dexterous hand series - check list dexterous hand series - check list dexterous hand series - check list dexterous hand series - check list
Upgradable With Other Components dexterous hand series - check list dexterous hand series - check list dexterous hand series - check list dexterous hand series - check list

Price List

Please get in touch via the contact form at the top of this page so that we can go through this with you. We may be able to offer a discount if you’re eligible for our Academic Partnership Programme.

dexterous hand series - dexterous series.png

Other hands in the series

Dexterous Series

The Dexterous Hand is also available in Lite, Extra Lite and Super Lite models. Each model is smaller, lighter and more cost-effective than the next. Removing the fingers we found makes the system lighter while still keeping our unique finger design, allowing you, the researcher, to still complete nimble tasks.

Get More From Your Shadow Dexterous Hand

dexterous hand series - openai shadow dexterous hand simulated camera grid.png

CASE STUDIES

OpenAI

OpenAI used the Shadow Hand to study ways of learning dexterity using the complex task of solving a Rubik’s cube single-handedly.

They trained their system entirely in simulation via reinforcement learning and the Shadow Dexterous Hand demonstrated the learnings in the real world.

dexterous hand series - shadow dexterous hand with boading balls.png

CASE STUDIES

Google Brain

Google Brain used the Shadow Hand to learn how to manipulate multiple objects using just a few hours of real-world data.

The team used a novel robot task planning technique involving deep dynamics models (DDM). You can read all about the impressive results in this article.

dexterous hand series - s.png

CASE STUDIES

Bielefeld University

Bielefeld University used a pair of Shadow Dexterous Hands in various Grasping and Manipulation tasks, from paper folding strategies to object grasping, using data from a vision system.

“With its unique, human-like design, the Shadow Hands serve as the perfect testbed to design, evaluate, and improve computational models of human manual intelligence.” – Prof. Dr Helge Ritter

Contact us

A quick and easy way to contact us is through our online form

shadowrobot.com uses cookies to improve user experience. To find out more, read Shadow Robot's cookie policy here.

Accept and Close