Isaac Sim 4.5 (5.0) on Ubuntu 22.04 (pip) - gkgkgk1215/else GitHub Wiki

Isaac Sim

conda create -n env_isaaclab python=3.10  # for 4.5 
conda create -n env_isaaclab5 python=3.11  # for 5.0
conda activate env_isaaclab (or env_isaaclab5)

pip install torch==2.7.0 torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cu128

pip install --upgrade pip

pip install 'isaacsim[all,extscache]==4.5.0' --extra-index-url https://pypi.nvidia.com  # 4.5
pip install isaacsim[all,extscache]==5.0.0 --extra-index-url https://pypi.nvidia.com    # 5.0

  • The installation path can be queried with the command pip show isaacsim.

  • Verification

conda activate env_isaaclab (or env_isaaclab5)

# note: you can pass the argument "--help" to see all arguments possible.
isaacsim

# experience files can be absolute path, or relative path searched in isaacsim/apps or omni/apps
isaacsim isaacsim.exp.full.kit

Rendering Issue

  • RTX 50 series have the known issue during real-time rendering in Ubuntu 22.04. To detour this, you need to set "Path tracing" and "Samples per pixel per frame" options at the beginning. Otherwise, the renderings will be noisy and blurred:
  • But this is ad hoc solution. The rendering is getting much slower. Recommend to use IsaacSim 5.0
simulation_app = SimulationApp({
    "renderer": "PathTracing",
    "samples_per_pixel_per_frame": 1,
    "headless": False,
})

Isaac Lab

  • Installation
sudo apt install git cmake build-essential
cd ~ && git clone https://github.com/isaac-sim/IsaacLab.git
cd ~/IsaacLab && ./isaaclab.sh --install
  • Verification
# Option 1: Using the isaaclab.sh executable
# note: this works for both the bundled python and the virtual environment
./isaaclab.sh -p scripts/tutorials/00_sim/create_empty.py

# Option 2: Using python in your virtual environment
python scripts/tutorials/00_sim/create_empty.py
  • Train your robot
./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task=Isaac-Ant-v0 --headless
./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task=Isaac-Velocity-Rough-Anymal-C-v0 --headless

Setup Python Path

  • (Necessary with conda) Add the following lines to ".bashrc"
# Isaac Sim root directory
export ISAACSIM_PATH="${HOME}/anaconda3/envs/env_isaaclab/lib/python3.10/site-packages/isaacsim"

# Isaac Sim python directory
export ISAACSIM_PYTHON_PATH="${HOME}/anaconda3/envs/env_isaaclab/bin"

# Set the IsaacLab_PATH environment variable to point to your Isaac Lab installation directory
export IsaacLab_PATH="${HOME}/IsaacLab"

# Set to use the IsaacLab modules
export PYTHONPATH=${ISAACLAB_PATH}/source
  • (Not necessary) If you want to run "python" outside conda, you should create soft link inside IsaacLab folder. The shell script(isaaclab.sh) refers _isaac_sim folder to use Isaac Sim python script(python.sh) which is under conda environment:
ln -s ${ISAACSIM_PYTHON_PATH}/python ${ISAACSIM_PYTHON_PATH}/python.sh
ln -s ${ISAACSIM_PYTHON_PATH} ${IsaacLab_PATH}/_isaac_sim

Orbitsurgical

cd ~ && git clone https://github.com/orbit-surgical/orbit-surgical
cd orbit-surgical && ./orbitsurgical.sh
  • If you move the orbit-surgical directory, then you need to re-setup the path, for example,:
cd ~/pycharmprojects/orbit-surgical && ./orbitsurgical.sh
  • Verification
cd ~/orbit-surgical
${IsaacLab_PATH}/isaaclab.sh -p source/standalone/environments/teleoperation/teleop_se3_agent.py --task Isaac-Lift-Needle-PSM-IK-Rel-v0 --num_envs 1 --teleop_device keyboard

IDE Setting in PyCharm

  • Set PyCharm interpreter as env_isaaclab in conda
  • If unresolved module with red underline, setting-project structure-add content root (~/IsaacLab/source/isaaclab)

rclpy in Python 3.11

  • ROS2 humble is basically installed with Python 3.11 in Ubuntu 22.04.

  • After ROS2 installation, you will need to install docker and then IsaacSim WS for ROS:

https://docs.isaacsim.omniverse.nvidia.com/5.0.0/installation/install_ros.html#enabling-rclpy-custom-ros-2-packages-and-workspaces-with-python-3-11

  • Install Docker
for pkg in docker.io docker-doc docker-compose docker-compose-v2 podman-docker containerd runc; do sudo apt-get remove $pkg; done

# Add Docker's official GPG key:
sudo apt-get update
sudo apt-get install ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc

# Add the repository to Apt sources:
echo \
  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
  $(. /etc/os-release && echo "${UBUNTU_CODENAME:-$VERSION_CODENAME}") stable" | \
  sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update

sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
  • Install IsaacSim ROS Workspace
cd ~ && git clone https://github.com/isaac-sim/IsaacSim-ros_workspaces.git
cd ~/IsaacSim-ros_workspaces && sudo ./build_ros.sh -d humble -v 22.04
  • If you need rclpy in Python 3.11 env, you will always run the source in advance:
source ~/IsaacSim-ros_workspaces/build_ws/humble/humble_ws/install/local_setup.bash
source ~/IsaacSim-ros_workspaces/build_ws/humble/isaac_sim_ros_ws/install/local_setup.bash
  • If you have 'GLIBCXX_3.4.30' error, upgrade libstdcxx
conda update -c conda-forge libstdcxx-ng libgcc-ng

Install dependencies for ROS2

pip install lark 
sudo apt install ros-humble-xacro

Material & Prop Assets

https://github.com/NVIDIA-Omniverse/PhysicalAI-SimReady-Materials?tab=readme-ov-file