47 Downloads (Pure)

Samenvatting

The deployment of Reinforcement Learning (RL) on physical robots still stumbles on several challenges, such as sample-efficiency, safety, reproducibility, cost, and software platforms. In this paper, we introduce MoveRL, an environment that exposes a standard OpenAI Gym interface, and allows any off-the-shelf RL agent to control a robot built on ROS, the Robot OS. ROS is the standard abstraction layer used by roboticists, and allows to observe and control both simulated and physical robots. By providing a bridge between the Gym and ROS, our environment allows an easy evaluation of RL algorithms in highly-accurate simulators, or real-world robots, without any change of software. In addition to a Gym-ROS bridge, our environment also leverages MoveIt, a state-of-the-art collision-aware robot motion planner, to prevent the RL agent from executing actions that would lead to a collision. Our experimental results show that a standard PPO agent is able to control a simulated commercial robot arm in an environment with moving obstacles, while almost perfectly avoiding collisions even in the early stages of learning. We also show that the use of MoveIt slightly increases the sample-efficiency of the RL agent. Combined, these results show that RL on robots is possible in a safe way, and that it is possible to leverage state-of-the-art robotic techniques to improve how an RL agent learns. We hope that our environment will allow more (future) RL algorithms to be evaluated on commercial robotic tasks.
Originele taal-2English
TitelThe 33rd Benelux Conference on Artificial Intelligence and the 30th Belgian Dutch Conference on Machine Learning (BNAIC/BENELEARN 2021)
SubtitelAI in ACTION Joint International Scientific Conferences on AI
RedacteurenLuis A. Leiva, Cédric Pruski, Réka Markovich, Amro Najjar, Christoph Schommer
Plaats van productieCCIS
UitgeverijSpringer
Hoofdstuk5
Pagina's239-253
Aantal pagina's15
Volume1530
ISBN van elektronische versie978-3-030-93842-0
ISBN van geprinte versie978-3-030-93841-3
DOI's
StatusPublished - 2022
Evenement33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning: 33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning - Luxembourg, Luxembourg
Duur: 10 nov 202112 nov 2021
https://bnaic2021.uni.lu/

Publicatie series

NaamCommunications in Computer and Information Science
UitgeverijSpringer
Volume1530
ISSN van geprinte versie1865-0929
ISSN van elektronische versie1865-0937

Conference

Conference33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning
Verkorte titelBNAIC/BeneLearn 2021
Land/RegioLuxembourg
Periode10/11/2112/11/21
Internet adres

Vingerafdruk

Duik in de onderzoeksthema's van 'MoveRL: To A Safer Robotic Reinforcement Learning Environment'. Samen vormen ze een unieke vingerafdruk.

Citeer dit