SimplerEnv
Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)
File Explorer
Download Latest Version (.zip)- google_robot_close_drawer_visual_matching.png
- google_robot_coke_can_visual_matching.png
- google_robot_move_near_visual_matching.png
- google_robot_open_drawer_visual_matching.png
- google_robot_pick_random_object.png
- google_robot_put_apple_in_closed_top_drawer.png
- widowx_carrot_on_plate_visual_matching.png
- widowx_put_eggplant_in_basket_visual_matching.png
- widowx_spoon_on_towel_visual_matching.png
- widowx_stack_cube_visual_matching.png
- fSpy_calibration_example.png
- teaser.png
- octo_drawer_variant_agg_alt_urdf.sh
- octo_move_near_variant_agg_alt_urdf.sh
- octo_pick_coke_can_variant_agg_alt_urdf.sh
- octo_bridge.sh
- octo_drawer_variant_agg.sh
- octo_drawer_visual_matching.sh
- octo_move_near_variant_agg.sh
- octo_move_near_visual_matching.sh
- octo_pick_coke_can_variant_agg.sh
- octo_pick_coke_can_visual_matching.sh
- octo_put_in_drawer_variant_agg.sh
- octo_put_in_drawer_visual_matching.sh
- rt1_drawer_variant_agg.sh
- rt1_drawer_visual_matching.sh
- rt1_move_near_variant_agg.sh
- rt1_move_near_visual_matching.sh
- rt1_pick_coke_can_variant_agg.sh
- rt1_pick_coke_can_visual_matching.sh
- rt1_put_in_drawer_variant_agg.sh
- rt1_put_in_drawer_visual_matching.sh
- rt1x_bridge.sh
- __init__.py
- argparse.py
- maniskill2_evaluator.py
- __init__.py
- octo_model.py
- octo_server_model.py
- __init__.py
- rt1_model.py
- __init__.py
- __init__.py
- action_ensemble.py
- google_robot_test_dataset_inference_rollout_gt_traj_in_sim.py
- octo_inference_real_video.py
- rt1_inference_real_video.py
- rt1_plot_dataset_inference_trajectory.py
- widowx_test_dataset_inference_rollout_gt_traj_in_sim.py
- __init__.py
- env_builder.py
- observation_utils.py
- __init__.py
- UbuntuMono-R.ttf
- __init__.py
- io.py
- metrics.py
- visualization.py
- __init__.py
- main_inference.py
- simple_inference_visual_matching_prepackaged_envs.py
- test_googlerobot.py
- test_object.py
- test_widowx.py
- analyze_sysid_results.py
- prepare_sysid_dataset.py
- sysid.py
- calc_metrics.py
- calc_metrics_evaluation_videos.py
- coacd_process_mesh.py
- merge_videos.py
- save_video_frame.py
- visualize_dataset.py
- .flake8
- .gitignore
- .gitmodules
- .pre-commit-config.yaml
- ADDING_NEW_ENVS_ROBOTS.md
- example.ipynb
- LICENSE
- ManiSkill2_real2sim
- pyproject.toml
- README.md
- requirements_full_install.txt
- setup.py
# Installation Guide
git clone https://github.com/simpler-env/SimplerEnv
Downloads the entire project code from GitHub to your computer.
cd SimplerEnv
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
- APT (Debian/Ubuntu κ³μ΄) Built into Debian/Ubuntu-based Linux distributions.
pip install numpy==1.24.4
Installs the package published on PyPI directly β no need to clone the source.
sudo apt install ffmpeg
Installs directly from the APT package repository (Debian/Ubuntu-based).
pip install tensorflow==2.15.0
Installs the package published on PyPI directly β no need to clone the source.
pip install tensorflow[and-cuda]==2.15.1 # tensorflow gpu support
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install numpy==1.24.4
Installs the package published on PyPI directly β no need to clone the source.
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
pip install tensorflow==2.15.0
Installs the package published on PyPI directly β no need to clone the source.
pip install -r requirements_full_install.txt
Installs the Python libraries listed in requirements.txt (or similar).
pip install tensorflow[and-cuda]==2.15.1 # tensorflow gpu support
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.