Reinforcement Learning of Robot Behavior based on a Digital Twin

Tobias Hassel, Oliver Hofmann

Abstract

A reinforcement learning approach using a physical robot is cumbersome and expensive. Repetitive execution of actions in order to learn from success and failure requires time and money. In addition, misbehaviour of the robot may also damage or destroy the test bed. Therefore, a digital twin of a physical robot has been used in our research work to train a model within the simulation environment Unity. Later on, the trained model has been transferred to a real-world scenario and used to control a physical agent.

Download


Paper Citation


in Harvard Style

Hassel T. and Hofmann O. (2020). Reinforcement Learning of Robot Behavior based on a Digital Twin.In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 381-386. DOI: 10.5220/0008880903810386


in Bibtex Style

@conference{icpram20,
author={Tobias Hassel and Oliver Hofmann},
title={Reinforcement Learning of Robot Behavior based on a Digital Twin},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={381-386},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008880903810386},
isbn={978-989-758-397-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Reinforcement Learning of Robot Behavior based on a Digital Twin
SN - 978-989-758-397-1
AU - Hassel T.
AU - Hofmann O.
PY - 2020
SP - 381
EP - 386
DO - 10.5220/0008880903810386