Code accompanying the paper: "Stable Motion Primitives via Imitation and Contrastive Learning" (under review, submitted to T-RO). For details, please refer to https://arxiv.org/pdf/2302.10017.pdf.
The current version of the paper can be cited using the following reference:
@article{perez2023stable,
title = {Stable Motion Primitives via Imitation and Contrastive Learning},
author = {P{\'e}rez-Dattari, Rodrigo and Kober, Jens},
journal = {arXiv preprint arXiv:2302.10017},
year = {2023}
}
This repository allows learning dynamical systems of multiple dimensions and orders.
This repository contains simulated experiments; however, this framework has also been tested using a KUKA LBR iiwa robot manipulator. These results are shown in https://youtu.be/OM-2edHBRfc.
You can install the package using poetry.
poetry install
Enter the virtual environment using:
poetry shell
Requirements can be found at pyproject.toml
.
`
In the folder src
run:
python train.py --params <params_file_name>
The parameter files required for the argument params_file_name
can be found in the folder params
.
python simulate_ds.py
python run_optuna.py --params <params_file_name>
If you run into problems of any kind, don't hesitate to open an issue on this repository.