GR00TN1.5
State‑of‑the‑art vision‑language‑action model for dexterous robot manipulation, enabling zero‑shot generalization across diverse embodiments via diffusion‑based action generation.
GR00T N1.5 is a vision‑language‑action (VLA) model for generalist robot control. The model supports multiple robot embodiments and is designed for dexterous, long‑horizon manipulation tasks.
Not supported
This model is currently not supported on any IoT chipset.
To see performance metrics for this model on other chipsets, click the button below.
View for other chipsetsTechnical Details
Input:RGB camera frames (one or more views), a natural language task instruction and robot proprioceptive state (joint positions/velocities).
Output:Action chunk representing predicted joint commands over the next N timesteps, generated via diffusion denoising.
Applicable Scenarios
- Robotics
License
Model:APACHE-2.0
Terms of Use:Qualcomm® Generative AI usage and limitations
Tags
- generative-ai
Supported IoT Devices
- Dragonwing IQ-8275 EVK
- Dragonwing IQ-9075 EVK
- Dragonwing IQ-X5121
- Dragonwing IQ-X7181
- Dragonwing Q-8750
- QCS8550 (Proxy)
Supported IoT Chipsets
- Qualcomm® QCS7181
- Qualcomm® QCS8275
- Qualcomm® QCS8550 (Proxy)
- Qualcomm® QCS8750
- Qualcomm® QCS9075
Related Models
See all models
Looking for more? See models created by industry leaders.
Discover Model Makers