Facts

• Company: Shadow Robot
• Product type: Hand
• Status: commercial
• Capability focus: Manipulation
• Website: https://shadowrobot.com/dexterous-hand-series/

Profile sections

• Summary
• Overview
• Market context
• Audience
• Workflow
• Capability
• Deployment environment
• Positioning tags
• Specifications
• Tags
• Timeline / Research
• Comparable Systems
• Sources

Summary

Shadow Dexterous Hand is Shadow Robot five-fingered robotic hand for advanced manipulation research. It provides human-like articulation and high-precision control for studying grasping, in-hand manipulation, teleoperation and robot-learning tasks.

Overview

Shadow Dexterous Hand is Shadow Robot five-fingered robotic hand for advanced manipulation research. It provides human-like articulation and high-precision control for studying grasping, in-hand manipulation, teleoperation and robot-learning tasks.

Market context

Anthropomorphic five-finger dexterous robot hand for manipulation research, AI/ML experimentation, tactile-sensing work and teleoperation.

• Target environment: Robotics labs, AI research settings, teleoperation systems and humanoid or arm-based manipulation testbeds.
• Workflow context: Dexterous grasping, tactile sensing, teleoperation, sim-to-real learning and manipulation research.
• Customer context: Researchers, labs, humanoid builders and AI teams needing a canonical high-DoF hand platform.
• Deployment model: Commercial specialist end-effector in Shadow Robot's Dexterous Hand series.
• Commercial maturity: Commercial and long-running research platform with public specs and broad research recognition.
• Adoption constraints: Adoption depends on cost, integration complexity, maintenance, control software, tactile requirements and task fit.
• Market position: Canonical dexterous-hand research platform for testing high-DoF manipulation, tactile sensing and learning workflows.
• Adjacent products: AGILINK SkillHand, Linker Hand L30, DexRobot DexHand021 Pro, OceanTrix hand

Audience

Researchers

Workflow

Dexterous grasping, tactile sensing, teleoperation, sim-to-real learning and manipulation research.

Capability

manipulation

Deployment environment

Robotics labs, AI research settings, teleoperation systems and humanoid or arm-based manipulation testbeds.

Positioning tags

• Audience: Researchers
• Workflow: Dexterous grasping, tactile sensing, teleoperation, sim-to-real learning and manipulation research.
• Capability: manipulation
• Deployment environment: Robotics labs, AI research settings, teleoperation systems and humanoid or arm-based manipulation testbeds.

Specifications

• Weight Range: 4.3 kg classic hand; 2.4 kg Lite; 2.1 kg Extra Lite; 1.8 kg Super Lite kg
• Dof: 20 actuated DOF plus 4 under-actuated movements on the classic five-finger hand; Lite variants range from 7-13 DOF
• Actuation: Tendon-driven architecture with DC motors
• Tactile Sensing: Over 100 sensors at up to 1 kHz; Shadow Tactile Fingertip options across the series
• Interface: EtherCAT host control loop; ROS open-source platform support
• Supported Platforms: Can be integrated with robot arms, including Universal Robots arm option in Shadow documentation
• Variant Summary: Classic Shadow Dexterous Hand plus Lite, Extra Lite and Super Lite variants trade fingers, actuators and weight for lower payload on mobile-manipulation or arm-mounted setups.

Tags

• Peer Group: Robot Hand, Dexterous robotic hand, Robot Hand Components
• Workflow: End Effector Manipulation
• Capability: Tactile Dexterity, Robotic Grasping, Force control
• Stack Layer: Robot end-effector, Manipulation stack layer
• Commercial Stage: Developer platform, Commercial product

Timeline / Research

• 2023-08-01 - Research Publication - DMFC-GraspNet: Differentiable Multi-Fingered Robotic Grasp Generation in Cluttered Scenes - DMFC-GraspNet predicts dense multi-finger robotic grasps in cluttered scenes.
• 2023-04-10 - Research Publication - PoseFusion: Robust Object-in-Hand Pose Estimation with SelectLSTM - The dataset uses an anthropomorphic Shadow Dexterous Hand for teleoperated object-in-hand pose collection.
• 2022-10-11 - Research Publication - A Multi-Agent Approach for Adaptive Finger Cooperation in Learning-based In-Hand Manipulation - The method treats each finger as an individual agent for cooperative in-hand manipulati…
• 2019-10-15 - Research Publication - OpenAI publishes Rubiks Cube robot-hand research using Shadow Dexterous Hand - OpenAI published its Rubiks Cube robot-hand work on October 15, 2019, using a human-like robotic hand fo…
• 2019-05-01 - Research Publication - Shadow Dexterous Hand teleoperation paper maps hand depth images to robot joint angles - The paper introduces TeachNet for markerless vision-based teleoperation of dexterous robotic h…
• 2019-04-17 - Funding - Innovate UK awards Shadow Robot GBP 650k innovation loan for touch-transmitting teleoperation - Innovate UK awarded Shadow Robot a GBP 650k innovation loan for remote-touch teleoperation technolog…
• 2018-09-17 - Research Publication - Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network - In this paper, we present TeachNet, a novel neural network architecture for intuitive and ma…
• 2018-08-01 - Research Publication - Learning Dexterous In-Hand Manipulation - We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a…
• 2018-06-24 - Partnership - Shadow Robot, SynTouch and HaptX demonstrate Tactile Telerobot - Shadow Robot said the Tactile Telerobot integrated its dexterous hand with SynTouch BioTac sensors and HaptX haptic gloves.
• 2018-02-26 - Research Publication - Multi-goal RL benchmark paper includes in-hand manipulation with Shadow Dexterous Hand - The paper presents robotics environments for multi-goal reinforcement learning with sparse bin…
• 2017-03-21 - Partnership - Shadow Robot starts Innovate UK semi-autonomous teleoperation project - Shadow Robot said an Innovate UK-backed semi-autonomous teleoperation demonstrator launched on March 1, 2017.

Comparable Systems

• DG-5F-S - Tesollo - Robotic Hand
• ROH-AP002 - OYMotion - Hand
• RH56DFX - Inspire Robots - End Effector
• RH56E2 - Inspire Robots - End Effector
• RH56F1 - Inspire Robots - End Effector
• Realhand L6 - RealHand - Dexterous Hand
• Realhand O6 - RealHand - Dexterous Hand
• OmniHand Pro 2025 - AGILINK - Hand