Skip to main content
Version: 7

MoveIt Pro ML on Jetson Devices

Required Version
This feature requires MoveIt Pro version 7.0 or newer.
warning

The following Dockerfile changes will not work unless you have setup GPU Acceleration and GPU Inference

The moveit_pro_ml package enables the use of machine learning models in MoveIt Pro behaviors. These ML behaviors can be run on higher end CPUs in a reasonable amount of time, but will not be performant on Jetson devices if the GPU isn't utilized.

Enabling a Jetson GPU with MoveIt Pro​

For Nvidia tegra release 36 (Jetson 6.0, cat /etc/nv_tegra_release to see your release), the following dependencies are tested to work. For other releases of Tegra, you may have to find which versions of cudnn, cudnn-dev, onnxruntime, and l4t you need, and modify the below URLs accordingly. See here for information on different versions of jetpack.

Add the following lines to your user_ws Dockerfile in the user-overlay stage:

RUN wget https://repo.download.nvidia.com/jetson/common/pool/main/c/cudnn/libcudnn8_8.9.4.25-1+cuda12.2_arm64.deb -q --show-progress --progress=dot:giga && \
    sudo dpkg -i libcudnn8_8.9.4.25-1+cuda12.2_arm64.deb && \
    rm libcudnn8_8.9.4.25-1+cuda12.2_arm64.deb

RUN wget https://repo.download.nvidia.com/jetson/common/pool/main/c/cudnn/libcudnn8-dev_8.9.4.25-1+cuda12.2_arm64.deb -q --show-progress --progress=dot:giga && \
    sudo dpkg -i libcudnn8-dev_8.9.4.25-1+cuda12.2_arm64.deb && \
    rm libcudnn8-dev_8.9.4.25-1+cuda12.2_arm64.deb

RUN wget -O onnxruntime_gpu-1.19.0-cp310-cp310-linux_aarch64.whl https://nvidia.box.com/shared/static/6l0u97rj80ifwkk8rqbzj1try89fk26z.whl -q --show-progress --progress=dot:giga && \
    pip install onnxruntime_gpu-1.19.0-cp310-cp310-linux_aarch64.whl && \
    rm onnxruntime_gpu-1.19.0-cp310-cp310-linux_aarch64.whl

And ensure that the GPU_INFERENCE section from the previous guide is enabled for the arm64 repo:

########################
# ENABLE GPU INFERENCE #
# ######################
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
    --mount=type=cache,target=/var/lib/apt,sharing=locked \
    apt-get update && apt-get install wget -y -q --no-install-recommends && \
    wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/arm/cuda-keyring_1.1-1_all.deb && \
...

Then rebuild Pro with moveit_pro build and your Jetson GPU should now be fully enabled for GPU Inference.