Communication publiée dans un ouvrage (Colloques, congrès, conférences scientifiques et actes)
Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space
ORSULA, Andrej; Geist, Matthieu; OLIVARES MENDEZ, Miguel Angel et al.
2024In 2024 International Conference on Space Robotics, iSpaRo 2024
Peer reviewed Dataset
 

Documents


Texte intégral
procgen_for_peg_in_hole_assembly.pdf
Preprint Auteur (4.1 MB) Licence Creative Commons - Attribution
Télécharger

Tous les documents dans ORBilu sont protégés par une licence d'utilisation.

Envoyer vers



Détails



Mots-clés :
Advanced learning; Autonomous assembly; Condition; Generalisation; Learning techniques; Peg-in-hole assembly; Reinforcement learnings; Robotic systems; Space infrastructures; Space robotics; Artificial Intelligence; Aerospace Engineering; Automotive Engineering; Control and Optimization
Résumé :
[en] The ability to autonomously assemble structures is crucial for the development of future space infrastructure. However, the unpredictable conditions of space pose significant challenges for robotic systems, necessitating the development of advanced learning techniques to enable autonomous assembly. In this study, we present a novel approach for learning autonomous peg-in-hole assembly in the context of space robotics. Our focus is on enhancing the generalization and adaptability of autonomous systems through deep reinforcement learning. By integrating procedural generation and domain randomization, we train agents in a highly parallelized simulation environment across a spectrum of diverse scenarios with the aim of acquiring a robust policy. The proposed approach is evaluated using three distinct reinforcement learning algorithms to investigate the trade-offs among various paradigms. We demonstrate the adaptability of our agents to novel scenarios and assembly sequences while emphasizing the potential of leveraging advanced simulation techniques for robot learning in space. Our findings set the stage for future advancements in intelligent robotic systems capable of supporting ambitious space missions and infrastructure development beyond Earth.
Disciplines :
Sciences informatiques
Auteur, co-auteur :
ORSULA, Andrej  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Space Robotics
Geist, Matthieu;  Cohere
OLIVARES MENDEZ, Miguel Angel ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Space Robotics
MARTINEZ LUNA, Carol  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Space Robotics
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space
Date de publication/diffusion :
27 septembre 2024
Nom de la manifestation :
International Conference on Space Robotics (iSpaRo)
Lieu de la manifestation :
Luxembourg, Luxembourg
Date de la manifestation :
24/06/2024–27/06/2024
Manifestation à portée :
International
Titre de l'ouvrage principal :
2024 International Conference on Space Robotics, iSpaRo 2024
Maison d'édition :
Institute of Electrical and Electronics Engineers Inc.
ISBN/EAN :
9798350367232
Pagination :
357-364
Peer reviewed :
Peer reviewed
Jeu de données :
Disponible sur ORBilu :
depuis le 14 novembre 2024

Statistiques


Nombre de vues
104 (dont 6 Unilu)
Nombre de téléchargements
69 (dont 0 Unilu)

citations Scopus®
 
0
citations Scopus®
sans auto-citations
0
OpenCitations
 
0
citations OpenAlex
 
0

Bibliographie


Publications similaires



Contacter ORBilu