Download
NVIDIA Isaac‑GR00T N1.5 is an open-source foundation model engineered for generalized humanoid robot reasoning and manipulation skills. It accepts multimodal inputs—such as language and images—and uses a diffusion transformer architecture built upon vision-language encoders, enabling adaptive robot behaviors across diverse environments. It is designed to be customizable via post-training with real or synthetic data. The vision-language model remains frozen during both pretraining and finetuning, preserving language understanding and improving generalization. Streamlined MLP connection between vision encoder and LLM with added layer normalization.
Features
- Pretrained on expansive humanoid datasets including real, synthetic, and internet-scale video data
- Dual-system cognitive architecture enabling reflex-like actions (System 1) and deliberate reasoning (System 2)
- Handles cross-embodiment tasks like single/bimanual object manipulation and multi-step context-rich tasks
- Open-source and customizable through post-training workflows
- Supports generalization across robot platforms using a unified model and weights
- Foundation model ecosystem with publicly available training data, blueprints, and task scenarios
Project Samples
License
Apache License V2.0Follow NVIDIA Isaac GR00T
Other Useful Business Software
Build Securely on AWS with Proven Frameworks
Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of NVIDIA Isaac GR00T!
