EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DFL-TORO: A One-Shot Demonstration Framework for Learning Time-Optimal Robotic Manufacturing Tasks

Alireza Barekatain, Hamed Habibi, Holger Voos

IEEE Access · 2024 · 12 · 161164-161184

DOI: 10.1109/access.2024.3486615 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Alireza Barekatain und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Luxembourg National Research Fund (FNR) through the Project “A Combined Machine Learning Approach for the Engineering of Flexible Assembly Processes Using Coll….

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents DFL-TORO, a novel Demonstration Framework for Learning Time-Optimal Robotic tasks via One-shot kinesthetic demonstration. It aims at optimizing the process of Learning from Demonstration (LfD), applied in the manufacturing sector. As the effectiveness of LfD is challenged by the quality and efficiency of human demonstrations, our approach offers a streamlined method to intuitively capture task requirements from human teachers, by reducing the need for multiple demonstrations. Furthermore, we propose an optimization-based smoothing algorithm that ensures time-optimal and jerk-regulated demonstration trajectories, while also adhering to the robot’s kinematic constraints. The result is a significant reduction in noise, thereby boosting the robot’s operation efficiency. Evaluations using a Franka Emika Research 3 (FR3) robot for a variety of tasks further substantiate the efficacy of our framework, highlighting its potential to transform kinesthetic demonstrations in manufacturing environments. Moreover, we take our proposed framework into a real manufacturing setting operated by an ABB YuMi robot and showcase its positive impact on LfD outcomes by performing a case study via Dynamic Movement Primitives (DMPs).

Förderung

  • Luxembourg National Research Fund (FNR) through the Project “A Combined Machine Learning Approach for the Engineering of Flexible Assembly Processes Using Coll…

Zitieren

APA

Barekatain, A., Habibi, H., & Voos, H. (2024). DFL-TORO: A One-Shot Demonstration Framework for Learning Time-Optimal Robotic Manufacturing Tasks. IEEE Access, 12, 161164-161184. https://doi.org/10.1109/access.2024.3486615

Vancouver

Barekatain A, Habibi H, Voos H. DFL-TORO: A One-Shot Demonstration Framework for Learning Time-Optimal Robotic Manufacturing Tasks. IEEE Access. 2024;12:161164-161184. doi:10.1109/access.2024.3486615

BibTeX
@article{Barekatain2024,
  author = {Barekatain, Alireza and Habibi, Hamed and Voos, Holger},
  title = {DFL-TORO: A One-Shot Demonstration Framework for Learning Time-Optimal Robotic Manufacturing Tasks},
  journal = {IEEE Access},
  year = {2024},
  volume = {12},
  pages = {161164--161184},
  doi = {10.1109/access.2024.3486615}
}
Kostenlos starten →