Installing the suite

Installation Guide

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.

Prerequisites

Before you begin, ensure your system meets the following requirements:

Hardware 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

Software Requirements

• Operating System: Ubuntu 20.04 or 22.04
• Packages: Docker and Nvidia Container Toolkit

Installation Using Docker

Requirements

• .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

  1. Generate NGC API Key
  2. Login with the NGC API as password

Username: $oauthtoken
Password: 

Building the Docker Image

1. Clone the repository and navigate to the docker directory:

   git clone https://github.com/abmoRobotics/isaac_rover_orbit
   cd isaac_rover_orbit/docker

2. Download terrains from Google Drive:
   1. Download from Google Drive: https://drive.google.com/file/d/1VXFTD2OgHcsQL_ifO81AzD2HDkA98h93/view?usp=sharing
   2. Unzip files in root folder of the git repository
3. Build and start the Docker container:

   ./run.sh
   docker exec -it orbit bash

4. 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

Native Installation

If you prefer to install the suite natively without using Docker, follow these steps:

1. Install Isaac Sim 4.1 through the Omniverse Launcher.

2. 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
   

3. 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]

4. 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