Skip to content

Latest commit

 

History

History
100 lines (72 loc) · 2.87 KB

INSTALL.md

File metadata and controls

100 lines (72 loc) · 2.87 KB
Raw

Installation

1. Initial Setup:

Create a conda environment with Python 3.8 and clone RoboPrompt repo:

conda create -n RoboPrompt python=3.8
conda activate RoboPrompt
pip install pip==24.0 # fixed required for YARR
git clone https://github.com/davidyyd/roboprompt.git
cd roboprompt

Please make sure you are using pip==24.0 when installing the dependencies.

2. PyRep and Coppelia Simulator:

Check instructions from the PyRep. Paste below for convenience:

PyRep requires version 4.1 of CoppeliaSim. Download:

Once you have downloaded CoppeliaSim, you can unzip the simulator and clone PyRep from git:

tar -xf <EDIT ME>/PATH/TO/COPPELIASIM.tar.xz

Add the following to your ~/.bashrc file: (NOTE: the 'EDIT ME' in the first line)

export COPPELIASIM_ROOT=<EDIT ME>/PATH/TO/COPPELIASIM/INSTALL/DIR
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$COPPELIASIM_ROOT
export QT_QPA_PLATFORM_PLUGIN_PATH=$COPPELIASIM_ROOT

Remember to source your bashrc (source ~/.bashrc) or zshrc (source ~/.zshrc) after this.

Install the PyRep package:

cd PyRep
pip install -r requirements.txt
pip install -e .

You should be good to go! You could try running one of the examples in the examples/ folder.

If you encounter errors, please use the PyRep issue tracker.

3. RLBench

Install the RLBench package:

cd RLBench
pip install -r requirements.txt
pip install -e .

4. YARR

Install the YARR package:

cd YARR
pip install -r requirements.txt
pip install -e .

5. RobotPrompt

Finally, install the dependencies for RobotPrompt:

pip install git+https://github.com/openai/CLIP.git
pip install -r requirements.txt

6. Setup Virtual Display

This is only required if you are running on a remote server without a physical display.

We provide a script to set up the virtual display in Ubuntu 20.04.

sudo apt update
sudo apt-get reinstall xorg freeglut3-dev libxcb-randr0-dev libxrender-dev libxkbcommon-dev libxkbcommon-x11-0 libavcodec-dev libavformat-dev libswscale-dev
sudo nvidia-xconfig -a --use-display-device=None --virtual=1280x1024

wget https://sourceforge.net/projects/virtualgl/files/2.5.2/virtualgl_2.5.2_amd64.deb/download -O virtualgl_2.5.2_amd64.deb
sudo dpkg -i virtualgl*.deb
rm virtualgl*.deb
nohup sudo X &

Any later command using display (e.g., dataset generation and evaluation) should be run with DISPLAY=:0.0 python ....

For more details, please refer to the PyRep.