Data-driven control of a weakly-instrumented excavator with deep learning
Résumé
This paper presents a data-driven approach for
controlling a weakly-instrumented excavator within a Virtual
Reality (VR) supervision environment. We address challenges
related to non-linear dynamics and limited sensor data by
focusing on arm movement control using both traditional and
advanced strategies, including Proportional-Integral-Derivative
(PID) controllers, Model Predictive Control (MPC), and Deep
Reinforcement Learning (DRL). Our results demonstrate the
effectiveness of these methods in achieving precise control despite
non-linearities and limited instrumentation, contributing to the
broader field of intelligent machine control.
Fichier principal
2024_10_25_phd_publication_icir_data_driven_control.pdf (1.76 Mo)
Télécharger le fichier
Origine | Fichiers produits par l'(les) auteur(s) |
---|