Learning control strategy in soft robotics through a set of configuration spaces

Ménager, Etienne; Duriez, Christian

Type de document :

Communication dans un congrès avec actes

Titre :

Learning control strategy in soft robotics through a set of configuration spaces

Auteur(s) :

Ménager, Etienne [Auteur]
Deformable Robots Simulation Team [DEFROST ]
Duriez, Christian [Auteur]

Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Deformable Robots Simulation Team [DEFROST ]
Université de Lille
Inria Lille - Nord Europe

Titre de la manifestation scientifique :

IEEE International Conference on Soft Robotics (RoboSoft)

Organisateur(s) de la manifestation scientifique :

IEEE

Ville :

San Diego (CA)

Pays :

Etats-Unis d'Amérique

Date de début de la manifestation scientifique :

2024-04

Date de publication :

2024-04

Mot(s)-clé(s) en anglais :

Modelling Control and Learning for Soft Robots.
Soft Robot Applications

Discipline(s) HAL :

Informatique [cs]/Robotique [cs.RO]

Résumé en anglais : [en]

The ability of a soft robot to perform specific tasks is determined by its contact configuration, and transitioning between configurations is often necessary to reach a desired position or manipulate an object. Based on ...
Lire la suite >The ability of a soft robot to perform specific tasks is determined by its contact configuration, and transitioning between configurations is often necessary to reach a desired position or manipulate an object. Based on this observation, we propose a method for controlling soft robots that involves defining a graph of configuration spaces. Different agents, whether learned or not (convex optimization, expert trajectory, and collision detection), use the structure of the graph to solve the desired task. The graph and the agents are part of the prior knowledge that is intuitively integrated into the learning process. They are used to combine different optimization methods, improve sample efficiency, and provide interpretability. We construct the graph based on the contact configurations and demonstrate its effectiveness through two scenarios, a deformable beam in contact with its environment and a soft manipulator, where it outperforms the baseline in terms of stability, learning speed, and interpretability.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Infrastructure technologique pour la recherche d'excellence en robotique

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Fichiers

document
Accès libre
Accéder au document

configuration_space_arxiv.pdf
Accès libre
Accéder au document

2402.13649
Accès libre
Accéder au document

document
Accès libre
Accéder au document

configuration_space_arxiv.pdf
Accès libre
Accéder au document

Learning control strategy in soft robotics ... BibTeX CSV Excel RIS

Fichiers

Learning control strategy in soft robotics ...

BibTeX

CSV

Excel

RIS