For CADRL, you need to create a virtual environment environment with python 3.6. and tensorflow 1.4.
We recommend using virtualenv & virtualenvwrapper.
- Install virtual environment and wrapper (as root or admin! with sudo) on your local pc (without conda activated. Deactivate conda env, if you have one active)
sudo apt install python3-pip
sudo pip3 install --upgrade pip
sudo pip3 install virtualenv
sudo pip3 install virtualenvwrapper
which virtualenv # should output /usr/local/bin/virtualenv- Create venv folder inside your home directory
cd $HOME && mkdir python_env # create a venv folder in your home directory- Add exports into your .bashrc or .zshrc:
echo "export WORKON_HOME=$HOME/python_env #path to your venv folder
export VIRTUALENVWRAPPER_PYTHON=/usr/bin/python3 #path to your python3
export VIRTUALENVWRAPPER_VIRTUALENV=/usr/local/bin/virtualenv
source /usr/local/bin/virtualenvwrapper.sh" >> ~/.zshrc # Change to .bashrc if using bash- If you are on Ubuntu 20.04, install python3.6-dev
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt-get update
sudo apt-get install python3.6-dev
sudo apt-get install python3.6-distutilsNote: You might need to restart your terminal at this point.
- Create virtual environment with python 3.6
source ~/.zshrc # Change to .bashrc if using bash
mkvirtualenv --python=python3.6 cadrl- Install packages inside your venv (venv always activated!):
pip install --extra-index-url https://rospypi.github.io/simple/ rospy rosbag tf tf2_ros --ignore-installed
pip install pyyaml catkin_pkg gym netifaces pathlib filelock pyqt5 mpi4py lxml scipy defusedxml matplotlib tensorflow==1.4Remember to activate the python3.6 virtual environment, before launching arena-bench.
If you followed the installation guide, you can do that by typing:
workon cadrlroslaunch arena_bringup start_arena.launch local_planner:=cadrl # Make sure that your virtual env/poetry is activatedFor more details regarding usage, please refer to our documentation
For more information about CADRL, please refer to the original publication paper
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent