Generate CUDA for a robot

GRiD’s code generator lives in grid_codegen/ in this repository. It produces a robot-specific grid.cuh header; generating the header does not compile or run CUDA. Complete the source installation first, including the Git submodules.

Generate a header

From the repository root:

grid-generate config/robot_assets/iiwa14.urdf --algorithm-list dynamics -o /tmp/iiwa_grid.cuh

--algorithm-list restricts emission to named algorithms or profiles. Omit it to use the full profile. Add -f for a floating base; use --no-mujoco-kernels to omit the additional MuJoCo-convention kernels. For collision geometry, see Collision code generation.

Generate from Python

from URDFParser import URDFParser
from grid_codegen import GRiDCodeGenerator

robot = URDFParser().parse("config/robot_assets/iiwa14.urdf")
generator = GRiDCodeGenerator(robot)
generator.gen_all_code(
    algorithm_list=["dynamics"],
    output_path="/tmp/iiwa_grid.cuh",
)

GRiDCodeGenerator is the Python class name, not a separate repository or installable module. GRiD’s code generator vendors GLASS device-side linear algebra into the header by default. Set vendor_glass=False when using an external glass.cuh on your C++ include path.

Use the generated code

• For Python applications, Python Wrappers (grid-rbd) handles generation, compilation and caching through grid_rbd.load_robot(...).

• For CUDA applications, include the header in a CUDA C++ translation unit. See GRiD’s code generator for the entry-point layers and Library-safe initialization and cleanup for allocation and cleanup.

• Use Fast Robot Setup to reduce large-robot build time and memory, and CUDA Validation And Performance Reporting to check generated results.