In this page we'll walk you through the installation process of our simulation. Since our simulation is built on top of IsaacSim, you will need an Nvidia GPU to run it.

Hardware requirement:

• An Nvidia GPU:
  • with 8+ GB of VRAM (some scenes will work on 4GB)
  • RTX Series 2000 or above
• A recent 12+ threads CPU
• 32GB of RAM. (for some scenes 16GB is enough)
• 10+ GB of free space

Operating System:

• Linux distros similar to Ubuntu 22.04 or 24.04.
• Windows is not supported.

1. Clone (or fork) the OmniLRS repository

git clone [email protected]:OmniLRS/OmniLRS.git
cd OmniLRS

2. Init the submodule

# Pulls WorldBuilder
git submodule init
git submodule update

3. Install Git LFS (only needed once per user per machine. Skip if you already have Git LFS installed)

curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
sudo apt install git-lfs
git lfs install

4. Pull the assets hosted via Git LFS: this includes large files such as textures, USD, ephemeris, etc. (if you already had Git LFS installed before git clone, the large files must have been already downloaded during the git clone process. So it is normal that this step is immediate)

git lfs pull

5. Download the DEMs of the lunar southpole (this can take a long time). This is optional, only needed for the large-scale environment. Note: this uses the 'sync' method so only files that differ from the cloud will be downloaded.

sudo snap install aws-cli --classic  # to install the official aws command line interface 
aws s3 sync s3://jaops-omnilrs-dataset/SouthPole ./assets/Terrains/SouthPole --no-sign-request
# the above bucket is in Europe (Frankfurt). For those closer to Japan, this command will be faster:
# aws s3 sync s3://jaops-omnilrs-dataset-jp/SouthPole ./assets/Terrains/SouthPole --no-sign-request

Before you venture forward, check that the assets folder has been created with success. tree -d -L 2 assets It should contain the following:

├── assets
│   ├── Ephemeris
│   ├── Terrains
│   |   ├── Lunalab
│   |   ├── Lunaryard
│   |   └── SouthPole
│   ├── Textures
│   └── USD_Assets
│       ├── common
│       ├── environments
│       ├── lunalab
│       ├── robots
│       └── rocks

Next, we strongly recommend following the docker installation steps.

Although not supported officially and not tested often, the install could also be done using a native installation.

Prerequisite: please follow the procedure here to install all the components required for the IsaacSim container instalation.

Once you're all set, build the OmniLRS docker image:

./omnilrs.docker/build_docker.sh

That's it! (make sure you downloaded the assets in the Common Installation Steps above)

See the getting started instructions to learn more about starting the simulation.

[TODO: update this section with Isaacsim 4.5]

[TODO: is GDAL still needed now that DEM data is downloaded in already processed format?]

The first thing that needs to be done before we proceed with the native installation is to install IsaacSim via the "workstation install". We support two version 2023.1.1 and 4.1.0. Though we'd recommend sticking to 2023.1.1 as there are some issues with renderings in 4.1.0.

Next here are the commands to install the dependencies and download the assets (we recommend that you run them one by one to adapt to any unforeseen issue in your system):

# Install GDAL
sudo apt install python3 python3-dev python3-pip
sudo apt-get install gdal-bin
sudo apt-get install libgdal-dev
version=$(gdal-config --version)

# Install Python packages for Isaac Sim  # note replace with your isaacsim version!
~/.local/share/ov/pkg/isaac_sim-2023.1.1/python.sh -m pip install opencv-python omegaconf hydra-core skyfield gdal==$version zfpy numba
python3 -m pip install --upgrade pip
python3 -m pip instal gdal==$version black

Once this is done you should be off to the races! See getting started to learn more about starting your first scene.