The collection of Gymnasium environments for the Aegis UR5e station.
- All poses consist of position
x,y,zand orientation in quaterion formqx,qy,qz,qw, i.e.:pose=[x,y,z,qx,qy,qz,qw] - For simplicity, the project uses Pytorch tensors instead of numpy ones.
poetry build
pip3 install ./dist/aegis_gym-*.whl
# Combined command:
poetry build && pip3 uninstall aegis_gym -y && pip3 install "./dist/aegis_gym-0.0.1-py3-none-any.whl[sim-genesis]"poetry run pytest -v -spython3 ./test/sb3_run_train.py- Generate standalone URDF model with aegis_ros/aegis_descrption launch command:
ros2 launch aegis_description generate_standalone_urdf.launch.py disable_cell:=trueWhich will generate the whole URDF file with 3D models in a default ~/ceai_ws/aegis_urdf directory.
- Run the
utils/upload_urdf_to_clearml.pyscript with the following options:
python3 utils/upload_urdf_to_clearml.py ~/ceai_ws/aegis_urdf --name AegisURDFModel --project AEGIS_GRASP --desc "Aegis simulator assets"Warning
To update the dataset make sure to add an additional option: --parent "PREVIOUS_DATASET_ID"
- Check the ClearML server's datasets.
In the robot's config set the urdf_model_id param to the ClearML's dataset ID.
Important
In case of failure to obtain the model, the code will try to load URDF model from ~/ceai_ws/aegid_urdf directory.
This project uses various tools for aiding the quality of the source code. Currently most of them are executed by the pre-commit. As a faster alternative it is suggested to use prek. Please make sure to enable its hooks:
# In case of pre-commit
pre-commit install
# In case of prek
prek installThis repository is licensed under the Apache 2.0, see LICENSE for details.
