The Unitree G1-D Standard D Humanoid Robot Platform (Revo 2 Basic Hands) is the fixed-base G1-D Standard D configuration that switches to the BrainCo Revo 2 five-finger dexterous hands (Basic Edition, RGB camera), emphasizing a more human-like five-finger grasp profile rather than three-finger dexterity.
The G1-D platform is built around a full-size humanoid upper body with a 17-DOF kinematic structure (excluding the end effector), a vertical lifting column with a 500 mm stroke for adjustable working height, and an integrated multi-sensor perception stack (head-mounted binocular vision plus wrist cameras) to support manipulation and teleoperation workflows; it is supplied with the standard control electronics/software stack and the required power/charging interface for deployment. As an authorized reseller with local support and logistics, RobotShop acts as a single point of contact for purchase and after-sales service, reducing friction versus a direct-from-manufacturer purchase and avoiding the need to ship the robot abroad for support or resolution.
Why Buy From RobotShop
Official Authorized Distributor
Genuine products with manufacturer-approved warranty coverage.
Locally Managed Logistics
Customs, inspection, and prep handled locally before shipment.
Single Point of Contact
Sales, support, and returns managed by one team.
FAQ & Knowledge Base
Docs, tutorials, and community answers to move faster.
Data & Training
Full-Stack Platform
for Humanoid Robot
Core Building Blocks
High-Output Humanoid Robot
Proprietary humanoid platforms built end-to-end with in-house actuators, gearsets, encoders, and integrated sensing.
Efficient Data Collection Suite
A single workflow covering the entire data lifecycle: capture, processing, annotation, validation, and dataset asset management.
End-to-End Training & Inference Toolkit
Supports distributed training, custom model creation, and smooth deployment, with compatibility across leading open-source frameworks.
Expanded Working
Envelope→
Expanded Working
Envelope
Mobile Operation: Uses a mobile lifting architecture that integrates wheels with a lifting mechanism
Vertical Workspace: 0–2m
Waist ROM (Z): ±155°
Waist ROM (Y): -2.5° ~ +135°
Faster, Low-Latency
Control→
Faster, Low-Latency
Control
Lifting Accuracy: ±0.5mm
End-Effector Gripper Accuracy: ±0.1mm
Note: Accuracy can vary depending on the end-effector configuration.
System Teleoperation Latency: <100ms
Sampling Rate: 60Hz
High-DOF Robot
Platform→
High-DOF Robot
Platform
Total Degrees of Freedom
Robot DOF (Excl. End-Effector): 19
Arm Degrees of Freedom: 7×2
Waist Degrees of Freedom: 2
Column Degrees of Freedom: 1
Base Degrees of Freedom: 2
(for motorized based only)
Optimized Data Acquisition Toolkit
Accelerate data collection and lower operating costs with flexible, standardized workflows — replacing slow, manual methods with a repeatable process.
Template-Driven Workflows for Faster Collection
Combines project coordination, task assignment, progress monitoring, and status reporting into one workspace. Using reusable templates, collection tasks can be created in a single click. Real-time visibility across the pipeline improves collaboration and keeps data acquisition running smoothly.
Flexible Setups Across Platforms & End Effectors
Supports data capture across multiple robot platforms and end-effector configurations. Strong standardization turns inputs from diverse devices into consistent, high-quality training-ready datasets through an end-to-end workflow.
Scalable, High-Concurrency Architecture
Designed to coordinate hundreds of robots performing synchronized data collection. With high-concurrency services and load-balanced scheduling, the platform reliably ingests and processes large, real-time data streams.
Always-On Collection, Stable & Reliable
Built on a highly available service foundation to support dependable 24/7 collection. Broad format compatibility lets outputs be used directly or converted into widely adopted training formats, speeding up R&D cycles.
Data Collection Pipeline
1
Create New
Data Collection
Tasks
2
Task Updates
and
Assignment
3
Data Capture
and
Annotation
4
Upload Data
and Review
5
Data Archiving
6
Dataset Export
Full-Stack Model Training & Inference Tools
Covers the complete workflow from data preparation to one-click deployment. The platform integrates smoothly with widely used open-source robotics model frameworks.
Broad Ecosystem with Popular Model Compatibility
An open model ecosystem with built-in community datasets and support for training on open-source datasets. It also provides deep integration with leading open-source models such as PI and GROOT.
Simulation Suite for Fast Model Validation
Includes a high-fidelity, high-precision 3D asset library. By building realistic simulation scenes, it quickly produces comprehensive evaluation plans to support algorithm verification.
Out-of-the-Box Experience for Quick Rollout
Ready to deploy immediately, reducing setup time. Kick off development with "one-click training," use integrated simulation for reliable evaluation, and transition smoothly from algorithms to real-world machines.
High-Efficiency Distributed Training
Built on a high-performance distributed training stack, enabling elastic task scheduling and parallel acceleration. It scales dynamically with available resources, achieving up to 90% GPU utilization.
Model Training & Deployment Workflow
1
Choose
Model
Architecture
2
Set Training
Configuration
3
Live Training
Monitoring
4
Parameter
Tuning
5
Run Simulation
Tests
6
Export & Deploy
Model
Application Scenario
Service
Life
Retail
Industry
UnifoLM-WMA-0:
An Open World-Model-Action (WMA) Framework
UnifoLM-WMA-0 is Unitree’s open-source world-model-action architecture across multiple robotic embodiments, built to support general-purpose robot learning. At its core is a world model that learns to interpret physical interactions between robots and the environments they operate in.
Decision-Making Mode:
Action Generation Guided by
Accurate Prediction
Using the current scene state and the task goal, the system forecasts upcoming physical interactions between the robot and its surroundings. These predictions help the policy module select actions, minimizing decision drift while improving the precision and consistency of motion execution.
Simulation Mode:
High-Fidelity Feedback for Data
Synthesis
It can also operate as an interactive simulator, generating high-fidelity environmental feedback from robot motion inputs. By producing realistic synthetic data, it becomes a strong source for model training and policy refinement—helping speed up learning and iteration.
[1] The maximum load of the arm varies greatly under different arm extension postures.
[2] For end-effector selection, please contact our sales team.
[3] For more information, please read the secondary development manual.
WARNING: This product can expose you to chemicals including lead and lead compounds, which are known to the State of California to cause cancer and birth defects or other reproductive harm. For more information go to: www.P65Warnings.ca.gov.
Refund Policy
If you are not satisfied with a product purchased from the Site, you may request a return within 30 days from the delivery date, unless the product is listed under the Return Exceptions below or is subject to specific return conditions noted on the product page.
This return policy also applies, as a minimum standard, to products sold and fulfilled by third-party vendors through the Marketplace.
Returns under this policy concern non-defective products. In the case of a confirmed manufacturing defect, remedies are handled under the Warranty terms, at the Vendor's discretion. See the Warranty section.
Return Conditions
To qualify for a refund under the 30-day return policy, all of the following conditions must be met:
A valid Return Authorization (RA) number must be obtained prior to returning the product. Returns without an RA number will be refused.
The RA number is valid for 30 days. The returned item must be received within that period.
The RA number must be included with the return.
Products must be returned in unused, unmodified condition (e.g., no scratches, alterations, missing parts, or signs of installation/use) and in their original packaging, suitable for resale.
Shipping fees are non-refundable. Return shipping costs are the responsibility of the customer, except in cases of a product confirmed defective through RobotShop's troubleshooting process or of a verified shipping error by RobotShop.
Refunds are processed within 7 days after receipt and inspection of the returned item.
A $100 cleaning fee may apply to domestic robots returned in used or unclean condition.
A 20% restocking fee may apply to large-quantity returns of items ordered specifically for the customer from the manufacturer or not part of RobotShop's standard inventory.
Return Exceptions
The following products are not eligible for return or refund under this policy:
Used, damaged, or modified products — Items that show signs of use, wear, or alteration, making them unsuitable for resale.
Consumables — Use and wear-and-tear components, altered or depleted through use (e.g., batteries, belts, brushes, gears, filament, tires, disposable bags, lubricants, greases, waxes, etc.). Not eligible for return once opened or used.
Perishables — Goods liable to deteriorate or expire rapidly. Not eligible for return.
Sealed goods (health or hygiene) — Items sealed for health-protection or hygiene reasons (e.g., masks, gloves, odor-absorbing products). Not eligible for return once unsealed.
Build-it-yourself products and items requiring customer assembly — Including robots & kits, robot parts, and other products requiring assembly or soldering. Not eligible for return once assembled, soldered, or installed.
Digital Goods, Software, and Apps — Final sale only, due to licensing restrictions.
Clearance Items — Products identified as clearance or final sale, including end-of-life or discontinued items.
Custom-made, personalized, or special-order items — Products manufactured, configured, adapted, or built to the customer's own specifications and requirements.
On-Demand Items — Standard catalogue products not stocked by RobotShop and ordered specifically to fulfill a customer request.
While the same return policy applies, these orders require a separate contact process for returns.
RobotShop Fulfilled Orders → submit a support ticket from your account under My Support Tickets.
Marketplace Vendor Orders → submit a ticket from your account under My Marketplace Tickets to contact the vendor directly.
Note: Marketplace vendor products are normally labelled with SKUs starting with RM, and identified on the product page with the mention "Sold and fulfilled by [Vendor Name]".