- Stock: In Stock
- Product code: 00-00014540
- Weight Brutto: 42.00kg
More from this brand
Unitree G1-D Ultimate C-U8 for Creating Datasets and Training AI-Based Robots
Unitree G1-D Ultimate C-U8 is a mobile humanoid robot on a wheeled differential base that combines all the key features of the basic version Ultimate A with an advanced manipulation system. The robot is designed for collecting multimodal data, testing precise manipulation algorithms, training robotic models, and autonomous navigation in real environments. With 33 degrees of freedom, the robot is equipped with two Dex3-1 Force-Controlled Three-Finger Dexterous Hands with tactile feedback and a built-in RGB camera. The humanoid robot moves independently, performs a 360° turn on the spot, and reaches speeds of up to 1.5 m/s. Each hand has 7 degrees of freedom, providing high precision in grasping objects of various shapes and materials.

Dexterous Hand Dex3-1 Specifications
- Type: Force-Controlled Three-Finger Dexterous Hand with tactile feedback
- Weight: approximately 650 g
- Dimensions: 175 x 88 x 77 mm
- Degrees of freedom per hand: 7 DoF (thumb 3 DoF, index finger 2 DoF, middle finger 2 DoF)
- Number of tactile (haptic) sensors: 33
- Power supply voltage: 12-58 V
- Standby current: 58 V @0.2A
- Communication interface: USB
- Additionally: built-in RGB camera

Key Technical Features
- Total number of degrees of freedom. 33 degrees of freedom, consisting of 7 degrees of freedom per hand (14 DoF), 2 degrees of freedom for the waist, 1 degree of freedom for the retractable column, 7 degrees of freedom per three-finger Dexterous Hand Dex3-1 (14 DoF), and 2 degrees of freedom for the mobile differential chassis.
- Mobile base for fieldwork. Two-wheeled differential drive supports a 360° turn on the spot and a movement speed of up to 1.5 m/s.
- Retractable column for changing working height. The platform height varies from 1260 mm to 1680 mm, and the column lift speed is approximately 60 mm/s.
- Base sensors for navigation. The chassis has LiDAR, two depth cameras, two physical collision sensors, and two low obstacle sensors.
- Three-finger Dexterous Hand Dex3-1. Each hand is equipped with a force-controlled three-finger Dexterous Hand Dex3-1 with 7 degrees of freedom, 33 tactile sensors, a built-in RGB camera, weighing approximately 650 g, and dimensions of 175x88x77 mm. The hand supports precise force control and tactile feedback.
- Vision system for data collection. The platform is equipped with a main HD binocular camera, two HD cameras on the wrists, and two built-in RGB cameras in the Dex3-1 hands.
- Computation for robotic tasks. The base platform has an 8-core high-performance CPU, and the enhanced performance module includes NVIDIA Jetson Orin 16GB with a performance of 100 TOPS.
- Wireless communication support. Unitree G1-D Ultimate C-U8 supports Wi-Fi 6 and Bluetooth 5.2.
- Support for updates and development. The platform supports Upgraded Intelligent OTA and Secondary Development.
- Working height up to 2 m. The lifting column with a stroke of 450 mm allows changing the working area height and performing manipulations at a height of up to 2 meters.
- Precise column positioning. The column provides positioning accuracy up to 1 mm, which is important for training robotic models and performing manipulation operations.
- Comprehensive multisensory system. The platform combines a stereo camera, wrist cameras, RGB cameras in hands, LiDAR, depth cameras, 33 tactile sensors on each hand, and collision sensors for comprehensive data collection and real-time navigation.
- Autonomous operation from two power systems. The upper module uses a quick-release 9000 mAh battery with a runtime of up to 2 hours, and the chassis is equipped with a built-in 30 Ah battery with autonomy up to 6 hours.
- User interaction tools. The robot supports an array of 4 microphones and a built-in 5 W speaker for voice interaction and audio notifications.
Design and Functionality
Unitree G1-D Ultimate C-U8 is a mobile dual-arm robotic platform with a retractable column, two 7-axis manipulators, and an advanced manipulation system based on three-finger Dexterous Hands. The robot combines high mobility with precise manipulation capabilities, making it an effective tool for data collection, algorithm testing, and robotic model training. The robot's dimensions are approximately 1260x525x570 mm in the lower position and 1680x525x570 mm in the upper, with a net weight with batteries reaching 80 kg.
Three-Finger Dexterous Hand Dex3-1
Unitree G1-D Ultimate C-U8 is equipped with two force-controlled three-finger hands Dex3-1 Force-Controlled Three-Finger Dexterous Hand with tactile feedback and a built-in RGB camera. Each hand has 7 degrees of freedom (thumb 3 DoF, index 2 DoF, middle 2 DoF), 33 tactile sensors, weighing approximately 650 g, and dimensions of 175x88x77 mm. The tactile system provides precise perception of pressure, friction, and contact direction, allowing delicate operations to grasp, hold fragile items, and collect high-quality multimodal data. The built-in RGB camera in each hand provides additional visual control directly in the capture area.
The manipulation system, along with 7-DoF arms, 2-DoF waist, lifting column, 7-DoF Dex3-1 hands, and 2-DoF chassis, forms a total of 33 degrees of freedom. Each arm has a working radius of about 0.45 m and a load capacity of up to 3 kg. The waist provides a range of motion Z: ±155°, Y: -2.5° ~ +135°, and the lifting column with a stroke of 450 mm, positioning accuracy of 1 mm, and lifting speed up to 60 mm/s allows reaching a working height of approximately 2 meters.
Multisensory Perception System
The robot is equipped with a comprehensive multisensory system, including a main HD binocular stereo camera with a resolution of 3840x1200 pixels, two HD cameras on the wrists 1920x1080, two built-in RGB cameras in the Dex3-1 hands, LiDAR on the chassis, two depth cameras, physical collision sensors, and a low-profile obstacle detection system.
The 33 tactile sensors on each hand complement visual and spatial data, providing full 3D mapping of the environment, precise distance determination, control of the manipulator's working area, and the collection of rich multimodal datasets for training computer vision models, tactile interaction, and autonomous navigation.
Robot Maneuverability and Movement
The mobility of Unitree G1-D Ultimate C-U8 is ensured by a two-wheeled differential chassis measuring 570x525x197 mm with 2 degrees of freedom. It supports a 360° turn on the spot and reaches a maximum speed of up to 1.5 m/s. For navigation, LiDAR, depth cameras, and an obstacle sensor system are used, allowing the implementation of modern algorithms for autonomous movement, localization, and route planning in real-time.

Computing Power and Model Development
Unitree G1-D Ultimate C-U8 is focused on intensive data collection and training of robotic models. The computing platform is built on an 8-core high-performance processor and an NVIDIA Jetson Orin 16GB module with a performance of up to 100 TOPS. This allows processing large volumes of data from cameras, LiDAR, tactile sensors, and other devices directly on board the robot.
The robot supports secondary development, OTA updates, wireless interfaces Wi-Fi 6 and Bluetooth 5.2, and comes with a separate computer for visualization. Additionally, it includes an array of 4 microphones and a 5 W speaker. ROS 2, Python, C++, DDS middleware, GStreamer, Gigabit Ethernet, USB, GPIO, and NVIDIA Jetson GPIO are supported.
Efficient Power System
Unitree G1-D Ultimate C-U8 is equipped with two independent power systems. The upper module operates from a quick-release 9000 mAh battery for up to 2 hours, and the chassis from a built-in 30 Ah battery (up to 6 hours of autonomous movement). The set includes a 54 V 5 A charger and a 51 V 10 A chassis charging station.
Application Areas
Unitree G1-D Ultimate C-U8 is designed for tasks related to data collection, model training, and algorithm testing in real environments. The mobile platform with three-finger tactile hands is particularly effective for research in precise manipulation, fine motor skills, and multisensory interaction with objects.
- Collection of tactile and visual data for humanoid robotics.
- Training and verification of fine motor skills and object grasping models.
- Testing motion control algorithms and five-finger hand.
- Research on human-robot interaction (HRI) in dynamic environments.
- Working with open-source datasets and models (PI, GROOT).
- Service, Life, Retail, and Industry scenarios.
- Research tasks with a mobile humanoid platform.
- Development of solutions for precise manipulations with tactile feedback.

Compatibility and Package
The platform is fully compatible with major robotic frameworks. The package includes: two Dex3-1 Dexterous Hands, batteries, chargers, NVIDIA Jetson Orin 16GB, documentation, and other equipment. Please specify the exact package when ordering.
Technical Specifications
| Specification | Value |
| Dimensions (min. column height) | 1260 x 525 x 570 mm |
| Dimensions (max. column height) | 1680 x 525 x 570 mm |
| Chassis dimensions net | 570 x 525 x 197 mm |
| Weight with batteries | Approximately 80 kg |
| Base type | Wheeled mobile (Wheel base Dual-Arm) |
| Total degrees of freedom | 33 |
| Degrees of freedom of one arm | 7 |
| Degrees of freedom of one hand | 7 |
| Number of joints of one hand | 11 |
| End effectors included | Dex3-1 Three-Finger Dexterous Hand x2 |
| Tactile sensors | Hantic Sensing (pressure, friction, direction) |
| Hand cameras | RGB camera x 2 (built-in hands) |
| Hand repeatability accuracy | 0.1° |
| Hand height | 160 mm (from the tip of the middle finger to the base of the palm) |
| Arm reach | Approximately 0.45 m |
| Maximum arm load | Approximately 3 kg |
| Degrees of freedom of the waist | 2 |
| Waist range of motion | Z: ±155°, Y: -2.5° ~ +135° |
| Column stroke | 450 mm |
| Column lift accuracy | 1 mm |
| Column lift speed | Max. 60 mm/s |
| Maximum working height | Approximately 2 m |
| Cooling system | Local air cooling |
| Upper part battery | Removable, 9000 mAh |
| Chassis battery | Built-in, 30 Ah |
| Autonomy | Up to 2 hours upper part / up to 6 hours chassis |
| Chargers | 54 V 5 A, 51 V 10 A charging station |
| Base processor | 8-core high-performance CPU |
| Computing module | NVIDIA Jetson Orin 16G 100 TOPS |
| Sensor system | HD camera 3840x1200, 2 HD cameras on wrists, 2 RGB cameras in hands, LiDAR, 2 depth cameras, tactile sensors, collision sensors |
| Microphones | Array of 4 microphones |
| Speaker | 5 W |
| Wireless interfaces | Wi-Fi 6, Bluetooth 5.2 |
| Chassis movement speed | 1.5 m/s |
| Chassis drive | Differential two wheels, 360° on the spot |
| Secondary development | Supported |
| OTA updates | Supported |
| Warranty | 12 months |
Operating Recommendations
- Plan work sessions considering battery life: approximately 2 hours for the upper part and approximately 6 hours for the chassis.
- For manipulation tasks, check the arm position, as the maximum load of up to 3 kg heavily depends on the manipulator's reach and position.
- Use data from 33 tactile sensors of Dex3-1 for calibrating grip force for specific objects and materials.
- Consider the capabilities of the built-in RGB cameras in the Dex3-1 hands, providing detailed visual control directly in the capture area.
- For navigation tests, leave enough space for the base to turn on the spot at 360°.
- Before data collection, set a clear task sequence: scenario creation, assignment, collection, annotation, verification, storage, and export.
- During machine learning tasks, check model compatibility with open-source datasets and frameworks such as PI or GROOT.
- Regularly calibrate the tactile sensors of the Dex3-1 hands before long sessions of tactile data collection.
- When working with fragile or non-standard objects, start with low grip force values and gradually increase it using tactile feedback.
Buy Humanoid Robot Unitree G1-D Ultimate C-U8
Order Unitree G1-D Ultimate C-U8 with price, specifications, and package clarification before payment. To order the humanoid robot, check availability and the required hand configuration.
| Details | |
| Battery Capacity (mAh) | 9 000 |
| Country of Origin | China |
| Warranty Period (months) | 18 |
| Weight & Dimensions | |
| Weight Netto (kg) | 35 |
| Dimensions Netto (mm) | 1320x450x200 |