Biological variability is enormous
Every plant is unique: leaf shape, stem stiffness, fruit mass, ripeness stage. Capturing this variability for perception and manipulation training is effectively impossible by hand.
Farm robotics, weeding, spraying, harvesting, autonomous tractors, need simulation environments with accurate crops, soil, implements, and equipment. Rigyd converts agricultural 3D models, images, or text into physics-enabled SimReady assets.
Updated 2026-05-08
Every plant is unique: leaf shape, stem stiffness, fruit mass, ripeness stage. Capturing this variability for perception and manipulation training is effectively impossible by hand.
Crops deform, branches bend, soil compresses, tools cut through material. Rigid-body approximations with default values miss how farm robots actually interact with biological materials.
A strawberry harvest model doesn't transfer to an apple orchard or a corn field. Each crop, each growth stage, and each implement needs its own physically accurate asset set.
Convert 3D plant scans and crop models into physics-enabled assets with realistic mass and collision geometry, calibrated against biological material density and surface properties.
Accurate mass and inertia estimation for tractors, implements, trailers, and tools, essential for autonomous tractor navigation and implement-coordinated training scenarios.
Soil, foliage, fruit skin, and machinery surfaces each have distinct friction coefficients. Rigyd's material identification produces calibrated per-region values for every asset.
Yes. Material identification distinguishes foliage, fruit skin, stems, and soil, assigning calibrated friction and mass values per region. Results are tuned for robotic interaction with biological materials.
Yes. Rigid-body physics estimation covers tractors, trailers, implements, and hand tools, with accurate mass and inertia for autonomous tractor navigation and implement-coordinated simulations.
Yes. Rigyd's bulk processing makes it practical to generate 1,000+ crop and equipment variants per growing season, covering ripeness stages, crop types, and equipment configurations.
Rigyd processes 3D mesh geometry (terrain heightmaps converted to mesh, field boundaries as USD prims). Direct GIS format ingestion (shapefile, GeoTIFF) isn't supported, convert through a GIS-to-3D pipeline first. Once converted, Rigyd handles per-region material identification for soil types, crop patches, and field boundaries, so terrain physics (soil compression, friction) reflects real-world variation across a farm.
Yes, via USD variants. A crop asset can carry multiple geometry variants (seedling → mature plant → harvest-ready) with per-stage physics overrides (plant stiffness, fruit mass, branch deformability under load). Switching variants in simulation is a runtime selection, so the same scene can sweep across the growing season without reloading assets. Useful for harvesting-policy training across crop maturity ranges.
Generate agricultural SimReady assets from 3D models, images, or text descriptions for farm robot training.
Tell us about your project and we'll be in touch shortly.