The NVIDIA Physical AI SimReady Warehouse OpenUSD Dataset is a high-precision 3D dataset released by NVIDIA in 2025 for robotics simulation and physical AI research. It aims to provide realistic industrial warehouse scenes and interactive objects for simulation platforms such as IsaacSim.

The dataset contains 753 OpenUSD 3D assets compatible with NVIDIA IsaacSim applications, with a compressed archive size of approximately 15 GB, covering warehouse environments, graspable objects, and various components. The data provides rich semantic labels (such as WikiData Q-Codes), physical properties (such as mass), and classification information, supporting tasks like image segmentation, object detection, and depth estimation. It is suitable for research in robotic grasping, navigation, and scene reconstruction.

Dataset Composition

• OpenUSD 3D Assets: A total of 753 assets, categorized into Scenarios, Assemblies, and Props, all pre-configured with USDPhysics colliders to support physical simulation.
• Asset Catalog: Includes a CSV file (physical_ai_simready_warehouse_01.csv) that details each asset’s preview image, name, relative path, category, tags, semantic Q-Code, mass (kg), and thumbnail path.
• Scene File: Provides a complete warehouse scene file (physical_ai_simready_warehouse_01.usd) as the starting point for simulation.
• Version Update: Version 1.1.0 adds a dedicated section of physically graspable objects specifically for robotic grasping tests.