-
Notifications
You must be signed in to change notification settings - Fork 1
Installing the suite
This guide provides detailed instructions for setting up the RL-suite using Docker, which simplifies the installation process of Isaac Sim, ORBIT, and our suite. Additionally, we provide steps for native installation.
Before you begin, ensure your system meets the following requirements:
- GPU: RTX GPU with at least 8 GB VRAM (Tested on NVIDIA RTX 3090 and NVIDIA RTX A6000)
- CPU: Intel i5/i7 or equivalent
- RAM: 32GB or more
- Operating System: Ubuntu 20.04 or 22.04
- Packages: Docker and Nvidia Container Toolkit
-
.Xauthority for graphical access: Run the following command to verify or create .Xauthority.
[ ! -f ~/.Xauthority ] && touch ~/.Xauthority && echo ".Xauthority created" || echo ".Xauthority already exists"
-
Nvidia Container Toolkit: see nvidia-container-toolkit
After installing the toolkit remember to configure the container runtime for docker using
sudo nvidia-ctk runtime configure --runtime=docker sudo systemctl restart docker
You may need to allow docker to access X server if you want to use the GUI:
xhost +local:docker
-
Login to NGC
- Generate NGC API Key
- Login with the NGC API as password
Username: $oauthtoken
Password:
-
Clone the repository and navigate to the docker directory:
git clone https://github.com/abmoRobotics/isaac_rover_orbit cd isaac_rover_orbit/docker
- Download terrains from Google Drive:
- Download from Google Drive: https://drive.google.com/file/d/1VXFTD2OgHcsQL_ifO81AzD2HDkA98h93/view?usp=sharing
- Unzip files in root folder of the git repository
-
Build and start the Docker container:
./run.sh docker exec -it orbit bash
-
Training an Agent Inside the Docker Container
To train an agent, use the following command inside the Docker container:
/workspace/orbit/orbit.sh -p train.py --task="AAURoverEnv-v0" --num_envs=256
If you prefer to install the suite natively without using Docker, follow these steps:
-
Install Isaac Sim 4.1 through the Omniverse Launcher.
-
Install Isaac Lab
git clone https://github.com/isaac-sim/IsaacLab cd Orbit # create aliases export ISAACSIM_PATH="${HOME}/.local/share/ov/pkg/isaac_sim-4.1" export ISAACSIM_PYTHON_EXE="${ISAACSIM_PATH}/python.sh" # Create symbolic link ln -s ${ISAACSIM_PATH} _isaac_sim # Create Conda Env ./orbit.sh --conda orbit_env # Activate Env conda activate orbit_env # Install dependencies conda --install
-
Set up the RL-suite:
# Clone Repo git clone https://github.com/abmoRobotics/isaac_rover_orbit cd isaac_rover_orbit # Install Repo (make sure conda is activated) python -m pip install -e .[all]
-
Running The Suite
To train a model, navigate to the training script and run:
cd examples/02_train/train.py python train.py
To evaluate a pre-trained policy, navigate to the inference script and run:
cd examples/03_inference_pretrained/eval.py python eval.py