The World’s Most Dexterous Humanoid Robot Hands Used in Research and Industry-Ready
A quick and easy way to contact us is via our short form below.
Each finger moves side to side independently (abduct, adduct), for unparalleled dexterity a total of 129 sensors to increase accuracy and enable high-level precision.
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.
Our most advanced 5-fingered Dexterous Hand is used by researchers all over the globe.
Almost all the capability of the Shadow Dexterous Hand in a smaller, lighter, cost-effective package. There’s no little finger (unnecessary for nimble tasks) or wrist (for easier mounting onto a broader range of robot arms).
Going an extra step further in lightness with our three-fingered Shadow Dexterous Hand Extra Lite.
The lightest of them all!
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|
|Easily Integrated on Robot Arms|
|Upgradable With Other Components|
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.
Produced by SynTouch, the BioTac is a revolutionary tactile sensor capable of detecting the full range of sensory information that human fingers can identify, including forces, micro-vibrations, and temperature.
Our Hands are more mobile when attached to an arm for extendable reach. We can provide each Hand with a safe and flexible 6 Degrees of Freedom (DOF) industrial robotic arm from Universal Robots.
The Hand is a key component in our Shadow Teleoperation System. The Hand can be controlled remotely to precisely mimic your movements and complete complex tasks over long distances – even cross-continent!
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.
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.
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
Whether you’re a researcher
or a company, feel free to reach out.
Live demos can be requested.