Dynamic modeling and AI-based control of a cable-driven parallel robot - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Dynamic modeling and AI-based control of a cable-driven parallel robot

Résumé

Controlling over-constrained cable-driven parallel robots (CDPRs) is a challenging task due to the complex dynamics of the system. Classical controllers require force distribution algorithms that involve an optimization problem, which is time consuming. In this paper, we propose an AI-based approach that learns a controller from simulated trajectories. A dynamic model of the CDPR is first validated experimentally on a real robot. Then, the controller is trained on the CDPR simulator with randomly generated trajectories using a deep deterministic policy gradient (DDPG). Finally, the trained controller is tested on different trajectories. Validation results show that the proposed approach is able to track unknown trajectories with a good accuracy.

Domaines

Automatique
Fichier principal
Vignette du fichier
IFAC23_1803.pdf (1.93 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04201285 , version 1 (20-11-2023)

Identifiants

Citer

Abir Bouaouda, Rémi Pannequin, François Charpillet, Dominique Martinez, Mohamed Boutayeb. Dynamic modeling and AI-based control of a cable-driven parallel robot. 22nd IFAC World Congress, IFAC 2023, Jul 2023, Yokohama, Japan. ⟨10.1016/j.ifacol.2023.10.868⟩. ⟨hal-04201285⟩
99 Consultations
41 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More