Installation using Isaac Sim pip

Installation using Isaac Sim pip#

Installing Isaac Sim#

From Isaac Sim 4.0 release, it is possible to install Isaac Sim using pip. This approach is experimental and may have compatibility issues with some Linux distributions. If you encounter any issues, please report them to the Isaac Sim Forums.

Attention

Installing Isaac Sim with pip requires GLIBC 2.34+ version compatibility. To check the GLIBC version on your system, use command ldd --version.

This may pose compatibility issues with some Linux distributions. For instance, Ubuntu 20.04 LTS has GLIBC 2.31 by default. If you encounter compatibility issues, we recommend following the Isaac Sim Binaries Installation approach.

  • To use the pip installation approach for Isaac Sim, we recommend first creating a virtual environment. Ensure that the python version of the virtual environment is Python 3.10.

    conda create -n isaaclab python=3.10
conda activate isaaclab

    # create a conda environment named isaaclab with python3.10
python3.10 -m venv isaaclab
# activate the conda environment
source isaaclab/bin/activate

    # create a virtual environment named isaaclab with python3.10
python3.10 -m venv isaaclab
# activate the virtual environment
isaaclab\Scripts\activate

  • Next, install a CUDA-enabled PyTorch 2.2.2 build based on the CUDA version available on your system.

    pip install torch==2.2.2 --index-url https://download.pytorch.org/whl/cu118

    pip install torch==2.2.2 --index-url https://download.pytorch.org/whl/cu121

  • Then, install the Isaac Sim packages necessary for running Isaac Lab:

    pip install isaacsim-rl isaacsim-replicator isaacsim-extscache-physics isaacsim-extscache-kit-sdk isaacsim-extscache-kit isaacsim-app --extra-index-url https://pypi.nvidia.com

Installing Isaac Lab#

Cloning Isaac Lab#

Note

We recommend making a fork of the Isaac Lab repository to contribute to the project but this is not mandatory to use the framework. If you make a fork, please replace isaac-sim with your username in the following instructions.

Clone the Isaac Lab repository into your workspace:

git clone git@github.com:leggedrobotics/IsaacLab-Internal.git

git clone https://github.com/leggedrobotics/IsaacLab-Internal.git

Get the Internal assets from git-lfs. You must install git-lfs before running the following commands:

cd IsaacLab-Internal
git lfs install
git lfs pull

Note

We provide a helper executable isaaclab.sh that provides utilities to manage extensions:

./isaaclab.sh --help

usage: isaaclab.sh [-h] [-i] [-f] [-p] [-s] [-t] [-o] [-v] [-d] [-c] -- Utility to manage Isaac Lab.

optional arguments:
   -h, --help           Display the help content.
   -i, --install [LIB]  Install the extensions inside Isaac Lab and learning frameworks (rl_games, rsl_rl, sb3, skrl) as extra dependencies. Default is 'all'.
   -f, --format         Run pre-commit to format the code and check lints.
   -p, --python         Run the python executable provided by Isaac Sim or virtual environment (if active).
   -s, --sim            Run the simulator executable (isaac-sim.sh) provided by Isaac Sim.
   -t, --test           Run all python unittest tests.
   -o, --docker         Run the docker container helper script (docker/container.sh).
   -v, --vscode         Generate the VSCode settings file from template.
   -d, --docs           Build the documentation from source using sphinx.
   -c, --conda [NAME]   Create the conda environment for Isaac Lab. Default name is 'isaaclab'.

isaaclab.bat --help

usage: isaaclab.bat [-h] [-i] [-f] [-p] [-s] [-v] [-d] [-c] -- Utility to manage Isaac Lab.

optional arguments:
   -h, --help           Display the help content.
   -i, --install [LIB]  Install the extensions inside Isaac Lab and learning frameworks (rl_games, rsl_rl, sb3, skrl) as extra dependencies. Default is 'all'.
   -f, --format         Run pre-commit to format the code and check lints.
   -p, --python         Run the python executable provided by Isaac Sim or virtual environment (if active).
   -s, --sim            Run the simulator executable (isaac-sim.bat) provided by Isaac Sim.
   -t, --test           Run all python unittest tests.
   -v, --vscode         Generate the VSCode settings file from template.
   -d, --docs           Build the documentation from source using sphinx.
   -c, --conda [NAME]   Create the conda environment for Isaac Lab. Default name is 'isaaclab'.

Installation#

  • Install dependencies using apt (on Ubuntu):

    sudo apt install cmake build-essential

  • Run the install command that iterates over all the extensions in source/extensions directory and installs them using pip (with --editable flag):

./isaaclab.sh --install # or "./isaaclab.sh -i"

isaaclab.bat --install :: or "isaaclab.bat -i"

Note

By default, this will install all the learning frameworks. If you want to install only a specific framework, you can pass the name of the framework as an argument. For example, to install only the rl_games framework, you can run

./isaaclab.sh --install rl_games  # or "./isaaclab.sh -i rl_games"

isaaclab.bat --install rl_games :: or "isaaclab.bat -i rl_games"

The valid options are rl_games, rsl_rl, sb3, skrl, robomimic, none.

Contents