This repo contains the implementation of ExoMy in Isaac Gym Preview 3 made by Group 666 (Spring 2022)
The setup specifically trains ExoMy to navigate in an unstructured Mars environment.
Training
training.mp4
Testing
trained_agent.mp4
- Ubuntu 18.04, or 20.04.
- Python 3.6, 3.7, or 3.8
- Minimum recommended NVIDIA driver version: 470.74 (470 or above required)
# Docker
curl https://get.docker.com | sh \
&& sudo systemctl --now enable docker
# Setting up NVIDIA Container Toolkit
distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
&& curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - \
&& curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
# Install the nvidia-docker2 package (and dependencies) after updating the package listing:
sudo apt-get update
sudo apt-get install -y nvidia-docker2
# Restart the Docker daemon to complete the installation after setting the default runtime:
sudo systemctl restart docker
- Download Isaac Gym from https://developer.nvidia.com/isaac-gym
- Unzip Isaac Gym
- nano isaacgym/docker/Dockerfile
- Insert the follwing code at the bottom of the file and save.
RUN git clone https://github.com/AAU-RoboticsAutomationGroup/isaac_rover_mars_gym.git /home/gymuser/isaac_rover_mars_gym
RUN pip3 install -e /home/gymuser/isaac_rover_mars_gym/.
RUN git clone https://github.com/Toni-SM/skrl.git /home/gymuser/skrl
RUN pip3 install -e /home/gymuser/skrl/.
WORKDIR /home/gymuser/isaac_rover_mars_gym
- bash docker/build.sh
- docker run -it -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY --network=host --gpus=all --name=isaacgym_exomy_container isaacgym /bin/bash #11. bash docker/run.sh DISPLAYPORT
- Enter container from different terminals --- sudo docker exec -it isaacgym_container bash
- cd isaacgymenvs
- python train.py
For other questions, contact
- Anton: abmo19@student.aau.dk
- Emil: etpe19@student.aau.dk
- Jacob: jknuds19@student.aau.dk