Install a wheel
Download the matching Linux x86_64 wheel from the v0.1.0 release.
Getting started
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.
Download the matching Linux x86_64 wheel from the v0.1.0 release.
Use an editable install when changing Python bindings or CUDA core code.
Use GHCR for the packaged Nav2 plugin smoke and benchmark path.
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.
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.
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.
No local setup needed: open the Colab quickstart.