Digital twin assets for
Unreal Engine
Create physics-enabled assets for Unreal Engine robotics simulations and digital twins. Automatic physics estimation, collision geometry, and OpenUSD output.
The problem
Why existing workflows fall short.
Physics setup is fragmented
Unreal Engine requires separate physics asset configuration, collision setup, and material assignments. Each asset needs individual attention.
Digital twins need thousands of objects
Factory and warehouse digital twins require massive libraries of physically accurate objects. Manual creation can't keep up.
Sim-to-real accuracy gap
Inaccurate physics parameters in UE simulations lead to policies that fail in the real world. Getting physics right is critical.
How Rigyd helps
AI-native infrastructure that automates the hard parts.
OpenUSD bridge to UE5
Rigyd outputs OpenUSD that imports directly into Unreal Engine 5 via the USD Stage Actor, maintaining physics properties.
Automated collision complexity
Convex decomposition generates collision geometry at configurable complexity — simple hulls for navigation, detailed meshes for manipulation.
Material-based physics
AI identifies materials from mesh geometry and appearance, then assigns calibrated friction, restitution, and density values.
cost reduction in digital twin asset creation
per asset, from upload to SimReady
better sim-to-real transfer with accurate physics
Build physics-accurate Unreal Engine simulations
Upload 3D models and get simulation-ready assets for UE5 in minutes.
Starts at $29/month. 30 credits included.
Frequently asked questions
How do Rigyd assets import into Unreal Engine 5?
Rigyd outputs OpenUSD that imports via UE5's USD Stage Actor. Mass, collision geometry, and material physics are applied automatically — no per-asset Physics Asset configuration required.
Can Rigyd handle digital twin scale for UE5?
Yes. Enterprise API has converted multi-thousand-object catalogs for factory and warehouse digital twins. Each asset is physics-validated, so the twin simulates operations — not just renders geometry.
Does Rigyd support UE5 Chaos Physics?
Yes. OpenUSD physics properties map to UE5's Chaos solver on import. Collision complexity is configurable — simple hulls for navigation, detailed convex decomposition for manipulation and contact-rich tasks.
How do Rigyd assets perform with Nanite and Lumen in UE5?
Visual meshes from Rigyd are Nanite-compatible — triangle counts are preserved from the source, so high-poly assets stream efficiently through Nanite's virtualized geometry. Collision meshes are kept as separate, low-poly convex decompositions, so Chaos contact detection stays fast while Nanite handles visual rendering. Lumen indirect lighting works against either visual mesh.
Can Rigyd populate UE5 Physics Asset settings automatically?
Yes. On USD import to UE5, Rigyd's physics metadata populates Static Mesh Component's simulation flags, collision presets, and physics material assignment. For articulated mechanisms, joint constraints and drive parameters auto-populate the Physics Asset Editor — eliminating per-link manual setup that's otherwise the slowest part of bringing a robot into Unreal. The same applies to Unreal's NVIDIA PhysX-based legacy projects: Rigyd's assets carry both Chaos- and PhysX-compatible attributes so the migration path between solvers stays open, useful for studios still on UE 5.0-5.2 evaluating when to switch.
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