Shadow Robot Dexterous Hand Series — Dexterous Hand, L/R
Understand this hand
Shadow’s full Dexterous Hand is a five-finger tendon-driven research system. Its manufacturer distinguishes 20 actuated DOF from 24 total joints and offers tactile configurations.
- What distinguishes it
- The full hand and the Lite variants differ in fingers, actuators and overall assembly mass. Select the exact configuration before comparing hardware.
- Before you build
- Confirm supplied tactile options, wrist and forearm scope, and the software release. Keep the overall assembly weight distinct from any hand-only figure.
Evidence review · 2026-09-25
Manufacturer, author and seller statements checked against public sources. This is not an independent hardware test. Fields outside this review retain their earlier evidence dates.
- Model / DOF
- 20 actuated axes, 24 joints, 5 fingers; series comparison checked. Source ↗
- Weight
- 4.3 kg overall assembly; isolated hand mass unreported. Excluded from hand-only mass sorting. Source ↗
- Sensing / software
- STF configuration and ROS are manufacturer-reported; installed options and supported releases need confirmation. Source ↗
- Price / availability
- Quote route; no numeric manufacturer price on this page. Stock and lead time unverified. Source ↗
Specifications
Record source date: 2026-09-16
Active / total DOF: 20 / 24
Joint position; 40 tendon-load sensors; 1 IMU; 2 standard / up to 5 Shadow Tactile Fingertips (STF)
Weight basis: 4.3 kg for one hand + forearm. Hand-only weight is not separately disclosed.
Availability / status: Current / marketed
Evidence limits: 24 joints include 2 wrist joints and coupled motion; 20 active DoF. 4.3 kg is overall assembly, not isolated palm.
Software, projects & datasets
What is ready to build with?
Manufacturer lists ROS integration; release compatibility not tested.
Product source ↗Check each link’s model scope, release, files and license. A reference is not a tested integration.
Dexhands has not reproduced a software setup or hardware test for this record. Published support is not a test result.
Curated public references, checked 2026-09-24. Links describe a model or family relationship, not hardware-tested compatibility.
Dexterous hand URDF collection
DexSuite · Family resource
Research-maintained visual and collision models for multiple hand families.
Inspect the model directory and upstream asset license; revision, size and sensor geometry may differ from your hand.
Hand motion retargeting
DexSuite · Family resource
Human-to-robot motion optimizers with configurations for the listed hand families.
Retargeting generates joint targets; it is not a device driver. Verify model geometry and joint order.
Shadow Hand ROS interface
Shadow Robot · Family resource
Manufacturer control interfaces and integration examples.
Select the matching hand configuration and ROS branch; Lite variants have different joints.
Shadow robot descriptions
Shadow Robot · Family resource
URDF descriptions and common packages for Shadow hardware.
Check joint count, hand side and hardware revision before using a model.
Shadow Hand in MuJoCo
Google DeepMind · Model-specific
Simulation assets for the E3M5 Shadow Hand, with left and right versions.
A simulation model, not a hardware driver. Match the E3M5 geometry to your unit.
DexGraspNet
PKU EPIC · Research use
Synthetic grasp data and generation code using a Shadow Hand model.
Simulation-generated grasps are not validated hardware executions.
UniDexGrasp
PKU EPIC · Research use
Vision-based dexterous grasp learning with Shadow Hand simulation tasks.
Follow the authors’ environment and model versions; deployment requires additional work.
Human-to-robot hand embodiment
DFKI Robotics Innovation Center · Research use
Research code for transferring human motions to several supported robot hands.
Use the project’s specific model, calibration and motion-capture assumptions; mesh licenses vary.
DexLearn grasp-synthesis baselines
DexLearn contributors · Research use
Learning-based grasp synthesis with documented Shadow-hand configurations.
Research model association only, not a verified driver for a current Shadow hardware revision. The README states noncommercial terms.
AffordDex: task-appropriate grasp contacts
AffordDex research team · Research use
Affordance-aware policy learning with released Shadow-hand simulation tasks.
Simulation research use; hardware support and reuse permissions must be checked separately.
Learn to audit a model-to-hand interface →