Towards Dynamic Obstacle Avoidance for Robot Manipulators with Deep Reinforcement Learning

Sie sind hier: Homepage > Suche

Towards Dynamic Obstacle Avoidance for Robot Manipulators with Deep Reinforcement Learning

Zindler, Friedemann / Lucchi, Matteo / Wohlhart, Lucas / Pichler, Horst / Hofbaur, Michael

We use reinforcement learning (RL) to demonstrate an easily reproducible setup to learn dynamic obstacle avoidance for a robotic arm based on sensory input as it follows a pre-planned trajectory. Training takes place exclusively in a simulation environment with random obstacle movements around the robot. We show that training dynamic obstacle avoidance in simulation translates well to the real environment with a UR5 manipulator and yields similar performance and success without further tuning of the learned policy. This is a step towards learning general skills needed to enable robots to operate in dynamic environments shared with humans. Source code, data and application videos are available at: https://www.robogym.net.

Zugriff

Zugriff prüfen

Verfügbarkeit in meiner Bibliothek prüfen

Bestellung bei Subito €

Exportieren, teilen und zitieren

Dokumentinformationen

Titel :

Towards Dynamic Obstacle Avoidance for Robot Manipulators with Deep Reinforcement Learning

Weitere Titelangaben:

Mechan. Machine Science

Beteiligte:

Müller, Andreas (Herausgeber:in) / Brandstötter, Mathias (Herausgeber:in) / Zindler, Friedemann (Autor:in) / Lucchi, Matteo (Autor:in) / Wohlhart, Lucas (Autor:in) / Pichler, Horst (Autor:in) / Hofbaur, Michael (Autor:in)

Kongress:

International Conference on Robotics in Alpe-Adria Danube Region ; 2022 ; Klagenfurt, Austria June 08, 2022 - June 10, 2022

Erschienen in:

Advances in Service and Industrial Robotics ; Kapitel : 11 ; 89-96

Mechanisms and Machine Science ; 120

Erscheinungsdatum :

2022-04-23

Format / Umfang :

8 pages

ISBN :

978-3-031-04870-8 , 978-3-031-04869-2

ISSN :