Payments and Security
Your payment information is processed securely. We do not store credit card details nor have access to your credit card information.
Description
- Unitree Dex5-1P Tactile Hand (Left)
- Designed for Unitree H1/H1-2 humanoid robots
- 20 Degrees of Freedom with Independent Finger Replacement
- 94 Tactile Sensors per Hand – Supports advanced tactile feedback
- 12 Pressure Sensors (94 pressure sensors in total)
- High-Speed Reflexes with Micro Force-Controlled Joints
- Ultra-Precise Fingertip Control with ±1mm repeat positioning accuracy
The Unitree Dex5-1P Tactile Hand for Unitree H1/H1-2 (Left) is a next-generation robotic hand engineered for high-performance humanoid applications, designed specifically for compatibility with the Unitree H1 and H1-2 robots. Featuring 20 degrees of freedom and individually replaceable fingers, the Dex5-1 sets a new benchmark in robotic dexterity. Each joint is designed for smooth backdrivability, eliminating the rigid, "stiff-hand" sensation and providing the fluid responsiveness required for reinforcement learning (RL) environments. Its four-finger lateral swing (±22°) enhances grip reliability, adapting intelligently to curved and irregular surfaces.
Built for both speed and sensitivity, the Dex5-1 integrates 94 tactile sensors per hand and supports secondary algorithm development, giving researchers and developers complete control down to the millimeter. High-power density hollow-cup motors, micro force-controlled transmission, and ultra-low damping joint design ensure lightning-fast reflexes and seamless motion. With fingertip positioning accuracy of ±1mm, gripping strength of up to 10N, and a load capacity of up to 4.5 kg, the hand offers both power and finesse.
From its ultra-small joint gap design that prevents snagging, to its 1000Hz communication rate and real-time perceptual feedback - including position, torque, stiffness, and IMU data - the Dex5-1 is engineered for high-fidelity interaction. Whether in academic research, advanced robotics training, or real-world manipulation tasks, the Unitree Dex5-1 delivers unmatched tactile control and adaptability.
- 1x Unitree Dex5-1P Tactile Hand for Unitree H1/H1-2 (Left)
- 217.3 x 127.5 x 72.1 mm (Note: The final shipped version may vary.)
- Minimum grip diameter: 10mm
- Fingertip Repeat Positioning Accuracy: ±1mm
Body Parameters
- Degrees of Freedom
- Thumb x 4
- Index Finger x 3
- Middle Finger x 3
- Ring Finger x 3
- Little Finger x 3
- Transmission Mechanism
- 12 self-developed micro force-controlled composite transmission joints (enable robot to achieve tactile proprioception)
- 4 micro force-controlled joint gear transmission
- Angle of Joint
- Thumb Joint:
- Thumb Joint 0: -33.5°~39°
- Thumb Joint 1: 0°~100°
- Thumb Joint 2: 0°~110°
- Thumb Joint 3: 0°~92°
- Four-Finger Joints:
- Knuckles 0: -22°~22°
- Knuckles 1: 0°~90°
- Knuckles 2: 0°~95°
- Knuckles 3: 0°~81°(Coupling with finger joint 2)
- Thumb Joint:
- Four-Finger Lateral Swing: ±22°
- Fingertip strength: 10N
- Working Voltage: 24V ~ 60V
- Static Current: 58V at 0.2A
- Maximum Current: 58V at 3A
- Communication Interface: USB 2.0
- Working Temperature Range: -20 °C ~ 60 °C
- Load Conditions (Palm facing down at room temperature, grasping a 5cm round hard object): Maximum Weight is 3.5 kg
- Load Condition (Palm facing left at room temperature, grasping a 5cm round hard object): Maximum Weight is 4.5 kg
- Weight: 1000 g
Sensing parameters
- Number of Pressure Sensors: 12 (94 pressure sensors in total)
- Array resolution
- 2 x 5 (Palm)
- 2 x 3 (Single Finger Pad) x5
- 2 x 3 (Single Fingertip) x5
- 2 x 3 (Single Finger Root) x4
- Range of Perception: 10 g - 2500 g
- Maximum Acceptance (Unamaged): 20 kg
Software functions
- Communication rate: 1000 Hz
- The number of bytes in a full packet
- Sender: 1234 bytes
- Receiver: 1270 bytes
- Perceptual feedback: Joint Mode, Joint Position, Joint Velocity, Joint Torque, Joint Temperature, Voltage and Current, imu Data
- Control feedback: Joint Mode, Joint Position, Joint Velocity, Joint Torque, Joint Stiffness Coefficient, Joint Damping Coefficient