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.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |