Isaac GR00T

Capabilities

• open VLA weights
• Isaac Lab training
• synthetic motion generation
• Jetson Thor deploy
• Isaac-Teleop
• GR00T-WholeBodyControl
• Multimodal Inputs
• Action Chunking
• Fine-tuning Support
• Isaac Lab Integration
• Isaac Sim Integration
• Robot Foundation Models
• Teleoperation (Isaac-Teleop)
• Whole-Body Control
• Simulation & Validation
• Policy Training
• Multimodal Input Processing
• Robot Foundation Model
• Sim-to-Real Teleoperation
• Hardware Adaptation
• Robot foundation models
• Multimodal reasoning (video, language, proprioception)
• Isaac-Teleop for demonstration collection
• Cross-embodiment generalization
• Sim-to-real transfer with Isaac Lab
• Fine-tuning on custom robot data
• Multimodal input processing
• Simulation frameworks (Omniverse/Cosmos)
• Whole-body control (GR00T-WholeBodyControl)
• Teleoperation data collection (Isaac-Teleop)
• CUDA-X accelerated runtime libraries
• humanoid robot model
• multimodal input
• whole-body control
• imitation learning
• reinforcement learning
• simulation validation
• manipulation tasks
• locomotion
• bimanual manipulation
• teleoperation
• simulation
• fine-tuning
• robot foundation model
• simulation integration
• sim-to-real transfer
• sim-to-real gap bridging
• humanoid robot control
• open robot foundation model
• simulation frameworks
• teleoperation data pipeline
• fine-tuning on custom embodiments
• Simulation Frameworks
• Teleoperation
• Multimodal Input
• Fine-tuning
• Proprioceptive state tracking
• Bimanual manipulation
• humanoid robotics
• foundation model
• multimodal inputs
• simulation-to-reality
• teleoperation support
• sim-to-real gap validation
• humanoid robot foundation model
• simulation workflows
• sim-to-real training
• sim-to-real translation
• simulation framework
• Humanoid Robotics
• Bimanual Manipulation
• Whole-body Control
• Sim-to-Real
• sim-to-real workflows
• fine-tuning support
• Humanoid Robot Control
• Fine-Tuning Support
• Teleoperation Support
• motion planning
• teleoperation demonstration
• humanoid robots
• Imitation Learning
• Simulation Validation
• Multi-step Tasks
• physics simulation
• Robot foundation model
• Multimodal input
• Sim-to-real training
• Whole-body control
• Imitation learning
• Humanoid robot control
• Multimodal inputs
• Simulation-to-reality validation
• sim-to-real validation
• language commands
• video input
• proprioceptive state
• action chunks
• teleoperation data collection
• robotics foundation model
• Simulation framework
• Fine-tuning support
• Open robot foundation model
• Simulation frameworks
• CUDA-X runtime libraries
• Real-time robot control
• Humanoid Robot Foundation Model
• Robot Teleoperation
• Simulation-to-Reality Gap Bridge
• simulation-to-real
• whole body control
• sim-to-real
• Humanoid Robots
• Physical AI
• Simulation workflows
• Teleoperation data pipelines
• teleoperation workflows
• simulation training
• Open reference platform
• Humanoid robotics
• Foundation Model
• Humanoid Control
• Teleoperation Workflows
• Humanoid Robot foundation model
• Teleoperation data pipeline
• Simulation validation
• Fine-tuning workflow
• simulation testing
• Humanoid robot foundation model
• Sim-to-real transfer
• Teleoperation Pipeline
• Simulation Framework
• humanoid robot reasoning
• Humanoid robot reasoning
• open reference platform
• Locomotion Control
• Simulation-to-Reality
• real-time robot inference
• 6D pose estimation
• Bipedal locomotion
• Simulation-to-real transfer
• Reinforcement learning
• Simulation-to-reality gap bridging
• Teleoperation data collection
• Fine-tuning on custom data
• Simulation integration
• Teleoperation reference
• Real-world & synthetic data training
• teleoperation workflow
• cross-embodiment generalization
• fine-tuning on custom robot data
• Open Robot Foundation Model
• Data Pipelines
• robot policy training
• humanoid robots foundation model
• humanoid robot platform
• foundation models
• VLA model
• policy training
• Foundation Models
• Robot Policies
• Pose Estimation
• humanoid robot policy
• physical AI
• robotic manipulation
• on-device inference
• Humanoid Robot Platform
• VLA Model
• Real-time Inference
• Visual SLAM
• robotic simulation
• Humanoid Robot Development Platform
• Simulation Workflows
• Robot Control
• Humanoid robot development
• Policy training
• Real-time inference and control
• robot foundation models
• open source
• TensorRT quantization
• Visual-Language-Action (VLA) model
• On-device inference
• Simulation-to-real workflow
• Open-source model code
• Sim and Real Workflows
• LeRobot Integration
• open VLA model
• teleoperation data capture
• policy evaluation in Isaac Lab-Arena
• on-device inference on Jetson Thor
• TensorRT NVFP4 quantization
• LeRobot integration
• Data Generation
• Jetson Thor Integration

Pricing

Shared model stack

Other tracked products running on the same foundation models — a quick read on how much of the catalog moves when one of these models changes.

Reported scale

Reference data. Each figure is whatever the source actually said — weekly users, downloads, revenue run-rate — with its own definition and date. These are not comparable between tools and are never used to rank anything.

No public usage figure on record for this product.

NVIDIA trades as NASDAQ: NVDA. Figures below are as reported for Q1 FY2027 on May 27, 2026; market levels are the close on Aug 6, 2026 and are a reference marker, not a live quote.

Change history

Isaac GR00T compared

Straight head-to-head pages against the busiest products in Robotics.