Index
Overview
Description:
GR00T N1.5 wave hand model is a vision language action model (VLA) fine-tuned to perform wave hand actions. It uses the weights and architecture from the NVIDIA Isaac GR00T N1.5, and is fine-tuned with simulation data from Unitree G1.
This model is ready for commercial and non-commercial use.
License/Terms of Use
Deployment Geography:
Global
Use Case:
This model is intended to be used within Isaac OS as a reference model.
References(s):
Model Architecture:
Architecture Type: Vision Language Action model
Network Architecture: GR00T N1.5
** This model was developed based on GR00T N1.5. ** This model has 3 billion parameters.
Input:
Input Type(s): Vision, State, Text (Language Instruction) Input Format:
- Vision: Variable number of 640x480 uint8 image frames, coming from cameras
- State: Floating Point (Robot Proprioception)
- Language Instruction: String
Input Parameters:
- Vision: Two-Dimensional (2D)
- State: One-Dimensional (1D)
- Language Instruction: One-Dimensional (1D)
Other Properties Related to Input:
- Vision: Red, Green, Blue (RGB) Image (640x480)
- State: Floating number vector
- Language Instruction: String
Output:
Output Type(s): Actions Output Format: Continuous-value vectors Output Parameters: Two-Dimensional (2D), 16x28 Tensor Other Properties Related to Output: Continuous-value vectors correspond to different motor controls on a robot, which depends on Degrees of Freedom of the robot embodiment.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Software Integration:
Runtime Engine(s):
- Pytorch - 2.5.1
- TensorRT - 10.11.0.33
Supported Hardware Microarchitecture Compatibility:
- NVIDIA Ampere
- NVIDIA Blackwell
- NVIDIA Hopper
- NVIDIA Lovelace
Preferred/Supported Operating System(s):
- Linux (Ubuntu 22.04/24.04 LTS)
The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.
Model Version(s):
GR00T N1.5 wave hand model for Unitree G1
Training:
Training Dataset:
** Data Modality
- Text
- Video
- Action
** Text Training Data Size
- Less than a Billion Tokens
** Video Training Data Size
- Less than 10,000 Hours
** Action Training Data Size
- For each frame in a video, there is a corresponding 1D action tensor with length 28.
** Data Collection Method by dataset
- [Human]
** Labeling Method by dataset
- [Human]
** Data Properties:
- Quantity: 1 episodes (1 simulation episode)
- Dataset Descriptions:
- Modalities: Multi-modal data consisting of (i) RGB video frames, (ii) text-based language instructions, (iii) robot state observations
- Nature of Content: Data from Isaac Sim simulation environment collected in human teleopetation; no personal data or copyright-protected content; data represents surgical instrument manipulation tasks
- Linguistic Characteristics: Language instructions describing surgical instrument handling operations
- Sensor(s):
- Vision sensors: One RGB camera to capture 640x480 pixel images
Inference:
Acceleration Engine: Pytorch / TensorRT Test Hardware:
- Ada RTX 6000
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please make sure you have proper rights and permissions for all input image and video content; if image or video includes people, personal health information, or intellectual property, the image or video generated will not blur or maintain proportions of image subjects included. For more detailed information on ethical considerations for this model, please see the Model Card++ Bias, Explainability, Safety & Security, and Privacy Subcards.
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Bias
| Field | Response |
|---|---|
| Participation considerations from adversely impacted groups protected classes in model design and testing: | None |
| Measures taken to mitigate against unwanted bias: | None |
Explainability
| Field | Response |
|---|---|
| Intended Task/Domain: | Robotic |
| Model Type: | Vision Language Action (VLA) Model |
| Intended Users: | Isaac OS users evaluating the model deployment with Unitree G1. |
| Output: | Action tensor (outputs the next 28 actions to do the wave hand actions) |
| Describe how the model works: | Accepts vision, language and robot observations, outputs robot action policy. |
| Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable |
| Technical Limitations & Mitigation: | This model was trained on data collected in a simulation environment. Therefore, this model is not expected to generalize to different robot platforms. |
| Verified to have met prescribed NVIDIA quality standards: | Yes |
| Performance Metrics: | Latency |
| Potential Known Risks: | This model may not correctly perform wave hand actions in circumstances with unexpected setups, inconsistent camera positioning, and environments not seen during training. |
| Licensing: | Nvidia License |
Privacy
| Field | Response |
|---|---|
| Generatable or reverse engineerable personal data? | No |
| Personal data used to create this model? | No |
| How often is dataset reviewed? | Before Release |
| Is there provenance for all datasets used in training? | Yes |
| Does data labeling (annotation, metadata) comply with privacy laws? | Yes |
| Is data compliant with data subject requests for data correction or removal, if such a request was made? | No, not possible with externally-sourced data. |
| Applicable Privacy Policy | https://www.nvidia.com/en-us/about-nvidia/privacy-policy/ |
Safety & Security
| Field | Response |
|---|---|
| Model Application Field(s): | Industrial/Machinery and Robotics |
| Describe the life critical impact (if present). | This model could pose significant risks if deployed on a robotic system in real environments without proper validation. This model has been tested with simulation data and limited real-world data using Isaac OS and may make unexpected movements if attempted to be deployed in a new environment. This model is not expected to generalize to different environments or robot platforms. |
| Use Case Restrictions: | Nvidia License |
| Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. |
- Downloads last month
- 38