CudaRobotics Docs

Getting started

Install CudaRobotics

Use the GitHub release assets for v0.1.0, build from a checkout for development, or run the Nav2 CUDA MPPI demo image from GHCR.

Release assets

Install a wheel

Download the matching Linux x86_64 wheel from the v0.1.0 release.

Source build

Develop from checkout

Use an editable install when changing Python bindings or CUDA core code.

Container

Run the demo image

Use GHCR for the packaged Nav2 plugin smoke and benchmark path.

Requirements

  • Linux x86_64 for the published wheel assets.
  • CUDA Toolkit 12.x for source builds.
  • A compatible NVIDIA driver at runtime.
  • CMake 3.18 or newer and a C++17 compiler for local builds.
  • ROS 2 and Nav2 build dependencies when building the controller plugin.

Release Assets

The v0.1.0 release intentionally distributes through GitHub assets, Colab, source builds, and GHCR.

python -m pip install ./cudarobotics-0.1.0-*.whl
python -c "import cudarobotics as cr; print(cr.__version__)"

Download assets from GitHub Releases. PyPI publishing is not part of v0.1.0.

Source Checkout

git clone https://github.com/rsasaki0109/CudaRobotics.git
cd CudaRobotics
python -m pip install -e python/
python examples/python/mppi_quickstart.py
python examples/python/registration_quickstart.py

Maintainers should run `./scripts/sync_python_core.sh` before building release artifacts so the Python package contains the current CUDA core.

Docker Demo

The published image loads the Nav2 plugin and runs the controller benchmark.

docker run --rm --gpus all ghcr.io/rsasaki0109/cuda-mppi-controller-demo:v0.1.0

# optional local build
docker build -f docker/Dockerfile -t cuda-mppi-demo .
docker run --rm --gpus all cuda-mppi-demo

See the Docker README for benchmark modes and output capture.

Colab

No local setup needed: open the Colab quickstart.