{"name":"NVIDIA Isaac GR00T: A Foundation Model for Generalist Robots","description":"NVIDIA Isaac GR00T N1.6 is an open vision-language-action (VLA) foundation model designed for generalized humanoid robot skills. It enables robots to perform manipulation tasks in diverse environments by taking multimodal input, including language and images. Researchers and professionals can leverage this model for fine-tuning on custom datasets and deploying it for inference.","github":"https://github.com/NVIDIA/Isaac-GR00T","url":"https://osrepos.com/repo/nvidia-isaac-gr00t","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/nvidia-isaac-gr00t","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/nvidia-isaac-gr00t.md","json":"https://osrepos.com/repo/nvidia-isaac-gr00t.json","topics":["robotics","AI","machine-learning","foundation-models","computer-vision","natural-language-processing","Jupyter Notebook","NVIDIA"],"keywords":["robotics","AI","machine-learning","foundation-models","computer-vision","natural-language-processing","Jupyter Notebook","NVIDIA"],"stars":null,"summary":"NVIDIA Isaac GR00T N1.6 is an open vision-language-action (VLA) foundation model designed for generalized humanoid robot skills. It enables robots to perform manipulation tasks in diverse environments by taking multimodal input, including language and images. Researchers and professionals can leverage this model for fine-tuning on custom datasets and deploying it for inference.","content":"## Introduction\nNVIDIA Isaac GR00T N1.6 is an open vision-language-action (VLA) foundation model engineered for generalized humanoid robot skills. This cross-embodiment model processes multimodal input, including language and images, to execute manipulation tasks across various environments. GR00T N1.6 is trained on a diverse mixture of robot data, encompassing bimanual, semi-humanoid, and extensive humanoid datasets, making it adaptable for specific embodiments, tasks, and environments through post-training. The N1.6 version introduces significant improvements over N1.5, including an updated model architecture with an internal NVIDIA Cosmos-Reason-2B VLM variant, a larger DiT, and enhanced pretraining data.\n\n## Installation\nTo get started with NVIDIA Isaac GR00T, you first need to clone the repository, ensuring submodules are included:\n\nsh\ngit clone --recurse-submodules https://github.com/NVIDIA/Isaac-GR00T\ncd Isaac-GR00T\n\n\nIf you've already cloned without submodules, initialize them separately:\n\nsh\ngit submodule update --init --recursive\n\n\nGR00T uses `uv` for dependency management. Ensure you have `uv v0.8.4+` installed. Then, set up the environment:\n\nsh\nuv sync --python 3.10\nuv pip install -e .\n\n\nCUDA 12.4 is recommended, though CUDA 11.8 has also been verified to work with compatible `flash-attn` versions. For a containerized setup, refer to the [Docker Setup Guide](https://github.com/NVIDIA/Isaac-GR00T/blob/main/docker/README.md \"Docker Setup Guide\" target=\"_blank\").\n\n## Examples\nNVIDIA Isaac GR00T offers a comprehensive workflow for robot control, from data preparation to evaluation. You can quickly start by downloading a pre-trained checkpoint and running the policy server for a specific embodiment, such as GR1:\n\nbash\n# On GPU server: Start the policy server\nuv run python gr00t/eval/run_gr00t_server.py --embodiment-tag GR1 --model-path nvidia/GR00T-N1.6-3B\n\n\nThe repository provides convenient scripts for validating zero-shot performance, fine-tuning the pre-trained GR00T N1.6 model on custom data, and running inference. Examples for various configurations and robot embodiments are available in the `examples/` directory. Detailed guides cover data preparation, inference, and fine-tuning for new embodiments. The project also supports academic simulation benchmarks like LIBERO, SimplerEnv, and RoboCasa for evaluation.\n\n## Why Use NVIDIA Isaac GR00T\nNVIDIA Isaac GR00T N1.6 is an invaluable resource for researchers and professionals in robotics. It provides a robust platform to:\n*   Leverage a pre-trained foundation model for advanced robot control.\n*   Efficiently fine-tune the model on small, custom datasets to adapt to specific tasks.\n*   Deploy the model for inference, enabling real-world robot applications.\nThe primary focus is on empowering users to customize robot behaviors through flexible fine-tuning capabilities, accelerating research and development in generalist robotics.\n\n## Links\n*   [Official Website](https://developer.nvidia.com/isaac/gr00t \"Official Website\" target=\"_blank\")\n*   [Model on Hugging Face](https://huggingface.co/nvidia/GR00T-N1.6-3B \"Model on Hugging Face\" target=\"_blank\")\n*   [Dataset on Hugging Face](https://huggingface.co/datasets/nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim \"Dataset on Hugging Face\" target=\"_blank\")\n*   [Research Paper (arXiv)](https://arxiv.org/abs/2503.14734 \"Research Paper (arXiv)\" target=\"_blank\")\n*   [NVIDIA Research Blog](https://research.nvidia.com/labs/gear/gr00t-n1_6/ \"NVIDIA Research Blog\" target=\"_blank\")\n*   [GitHub Repository](https://github.com/NVIDIA/Isaac-GR00T \"GitHub Repository\" target=\"_blank\")\n*   [License (Apache-2.0)](https://github.com/NVIDIA/Isaac-GR00T/blob/main/LICENSE \"License (Apache-2.0)\" target=\"_blank\")","metrics":{"detailViews":2,"githubClicks":4},"dates":{"published":null,"modified":"2025-12-30T12:01:03.000Z"}}