Introducing DEX-EE the most robust dexterous robot hand on the market.
A transformational advance in machine learning robots.
Designed and built for the world's leading AI research team
The Shadow Robot company has developed a new robot hand in collaboration with Google DeepMind to meet the needs of their real-world machine-learning projects.
Now available for purchase, DEX-EE is an ideal hardware platform for dexterous manipulation research. Delivering dynamic and controlled motion in a robust and reliable package, enabling long-running experiments without interruptions due to hardware failure.
DEX-EE’s high-speed sensor networks provide rich sensor data, including position, force and inertial measurement, as well as hundreds of channels of tactile sensing per finger. Shadow’s groundbreaking fingertip sensors offer hundreds of taxels each, with a massive dynamic range.
Transforming your research
High bandwidth torque and position control loops give delicate and precise fingertip dexterity
Torque and inertial measurement throughout makes the whole hand sensitive to interactions with its environment
Stereo camera-based fingertip tactile sensors provide an unprecedented level of 3D interaction detail in a robust package
Multi-taxel, 3 DOF tactile sensors on middle and proximal phalanges give additional information during grasping and manipulation
Easy for users to maintain with minimal training and designed to reduce instances of failure and downtime, with fail-safes and a graceful shutdown routine.
Fully ROS integrated for use as a research and development tool.
Robustness
Designed to reliably meet the needs of long-running reinforcement learning experiments
Long mean time to failure and reduced time for repair, resulting in high availability
Resistant against repeated impacts from its environment and aggressive use from an untrained policy.
Case studies
OpenAI
We’ve worked with OpenAI, founded by business tycoons, Elon Musk and Sam Altman to advance research within AI and machine learning using the Shadow Dexterous Hand.
- 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.
- Shadow Dexterous Hand demonstrated the learnings in the real world. No fine-tuning needed.
- Featured on BBC News and the front page of the New York Times.
Click Here
Case studies
Human Brain Project (HBP)
HBP and Maastricht University successfully integrate and simulate the Shadow Hand on the HBP Neurorobotics Platform which connects a physics simulator to a variety of neural networks (or brains).
- The Human Brain Project added the virtual Shadow Hand to their EBRAINS infrastructure to learn more about how the brain coordinates complex hand movements.
- Each Shadow Hand joint can be individually linked to both the input and/or output of the brain.
- Contact-based feedback is forwarded to the brain. No need for time-consuming physical setups.
Click Here
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).
- They were able to manipulate multiple objects with just four hours of real-world data.
- More info about the impressive results in this article.
Click Here
Previous slide
Next slide
Cutting edge collaboration
Shadow works with our customers long term to provide support and engineering services, and collaborate on development.
Developing DEX-EE has opened up significant technological advances and specialist knowledge which can be leveraged in a wide range of academic and applied research contexts.
Our consultancy service can help you identify what works for your project.