### Setting up RoboEXP Environment (Shell) Source: https://github.com/jianghanxiao/roboexp/blob/master/README.md Commands to set the CUDA home directory, create and activate a Conda environment with Python 3.8, and run scripts to install dependencies and download pretrained models required for the RoboEXP system. ```Shell # Here we use cuda-11.7 export CUDA_HOME=/usr/local/cuda-11.7/ # create conda environment conda create -n roboexp python=3.8 conda activate roboexp # Install the packages bash scripts/install_env.sh # download pretrained models bash scripts/download_pretrained_models.sh ``` -------------------------------- ### Downloading Calibration Files (Shell) Source: https://github.com/jianghanxiao/roboexp/blob/master/README.md Commands using `gdown` to download the calibration board file and an example calibration result file, which are necessary for performing wrist camera calibration for the RoboEXP system. ```Shell # Download the calibration board gdown 1KWYncDGjtGthePC3wzCu9zBW0nZI0RBM # Download the example calibration result gdown 1b2yp45eJVyXnOg11OImTER3zMRUcaZRN ``` -------------------------------- ### Running RoboEXP Interactive Exploration (Python) Source: https://github.com/jianghanxiao/roboexp/blob/master/README.md Command to execute the main interactive exploration script (`interactive_explore.py`) for the RoboEXP system. The script can be configured to enable visualizations by setting a flag. ```Shell # Set `visualize=True` to enable visualizations python interactive_explore.py ``` -------------------------------- ### Citing RoboEXP Paper (BibTeX) Source: https://github.com/jianghanxiao/roboexp/blob/master/README.md BibTeX entry for citing the RoboEXP paper presented at CoRL 2024. This provides the necessary information for academic citations. ```BibTeX @article{jiang2024roboexp, title={RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation}, author={Jiang, Hanxiao and Huang, Binghao and Wu, Ruihai and Li, Zhuoran and Garg, Shubham and Nayyeri, Hooshang and Wang, Shenlong and Li, Yunzhu}, journal={CoRL}, year={2024} } ``` === COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.