SimReady assets for
NVIDIA Isaac Sim
Upload any 3D model and get physics-enabled OpenUSD assets validated for Isaac Sim. Rigyd estimates mass, friction, restitution, and generates collision meshes automatically.
The problem
Why existing workflows fall short.
Manual physics annotation is slow
Isaac Sim requires USDPhysics schemas with rigid body, collision, and mass APIs. Manually annotating each asset takes hours per object.
Limited SimReady library
NVIDIA's SimReady library has ~1,000 assets. A single warehouse simulation can require 50,000+ unique objects with accurate physics.
Format conversion headaches
Getting .glb, .fbx, or .obj files into Isaac Sim-compatible OpenUSD with proper physics schemas requires multiple tools and manual steps.
How Rigyd helps
AI-native infrastructure that automates the hard parts.
Direct OpenUSD output
Rigyd outputs validated OpenUSD with PhysicsRigidBodyAPI, PhysicsMassAPI, and PhysicsCollisionAPI — ready to drop into Isaac Sim.
AI-powered physics estimation
Mass, friction, restitution, and center of mass are estimated automatically using multi-view analysis and a calibrated materials database.
Collision mesh generation
Automatic convex decomposition (V-HACD) generates collision geometry optimized for Isaac Sim's PhysX runtime.
cost reduction vs manual asset preparation
per asset, from upload to SimReady USD
assets generated for Isaac Sim workflows
Start building simulations in Isaac Sim faster
Upload your first 3D model and get a physics-enabled OpenUSD asset in minutes.
Starts at $29/month. 30 credits included.
Frequently asked questions
Does Rigyd output valid USDPhysics schemas for Isaac Sim?
Yes. Rigyd emits OpenUSD with PhysicsRigidBodyAPI, PhysicsMassAPI, and PhysicsCollisionAPI applied — the exact schemas Isaac Sim's PhysX runtime expects. Assets drop into Isaac Sim without additional physics authoring.
How is Rigyd different from NVIDIA's SimReady asset library?
NVIDIA's SimReady library is ~1,000 curated assets for general use. Rigyd converts your own 3D catalog — typically 10,000 to 50,000 SKUs — into SimReady OpenUSD automatically, so simulations match the environment your robots actually operate in.
What file formats can I upload for Isaac Sim conversion?
Rigyd accepts .glb, .fbx, and .obj files. No pre-processing needed — geometry cleanup, collision mesh generation via V-HACD, and physics annotation happen automatically. Output is Isaac-Sim-ready OpenUSD in ~5 minutes per asset.
Are Rigyd outputs compatible with Isaac Lab and Isaac Sim 5.0?
Yes. Rigyd outputs standard USDPhysics schemas (PhysicsRigidBodyAPI, PhysicsMassAPI, PhysicsCollisionAPI) which are version-stable across Isaac Sim releases. Assets work in Isaac Sim 4.x, Isaac Sim 5.0, and Isaac Lab without modification. Articulation root and joint schemas are also standard USDPhysics, so robot assets and articulated mechanisms transfer cleanly across the stack.
How fast do Rigyd-generated assets load into Isaac Sim?
Load time scales with collision-mesh complexity. Rigyd tunes V-HACD parameters per asset class — typically 16-32 convex hulls per graspable object — so loads stay under 100ms per asset on an RTX-class GPU. For warehouse-scale scenes with 10,000+ instanced assets, USD references mean only unique geometry loads once. Memory overhead is negligible compared to manual high-poly collision approximations.
Related reading
In-depth guides on robotics simulation, OpenUSD, and SimReady assets.
21 MAY 2026
Synthetic data generation for computer vision in robotics
Real-world labeled robotics data is expensive and slow to capture. Synthetic data is fast and unlimited — but only useful if the underlying simulation has correct physics, semantic labels, and domain randomization. Here's the complete pipeline.
18 MAY 2026
Digital twin creation pipeline for manufacturing
A factory digital twin needs every object to behave physically, not just render. This is the end-to-end pipeline: CAD intake, BIM merge, physics layer, semantic labeling, simulation runtime — at the asset volumes (10K+ unique SKUs) real factories actually contain.
13 MAY 2026
How to set up mass, friction, and joint properties for robot training
The three pillars of robot physics setup — mass, friction, joints — determine whether your trained policy transfers to real hardware. Here's the calibration target for each, the schemas, and the common mistakes that quietly break training.
Explore more
SimReady for Isaac Sim
OpenUSD assets validated for NVIDIA Isaac Sim
Models for MuJoCo
Physics-accurate assets for robot learning
Assets for Gazebo
Simulation-ready models for ROS 2
Warehouse Simulation
50,000+ SKUs need physics properties
Humanoid Robots
Whole-body interaction training assets
Sim-to-Real Transfer
Close the gap with accurate physics data