EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Informed Neural Networks for Unmanned Aerial Vehicle System Estimation

Domenico Bianchi, Nicola Epicoco, Mario Di Ferdinando, Stefano Di Gennaro, Pierdomenico Pepe

Drones · 29.11.2024 · 8 (12) · 716

DOI: 10.3390/drones8120716 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 29.11.2024. Verfasst von Domenico Bianchi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union Project ECSEL—Joint Undertaking RIA—2018 “Comp4Drones”, MAECI Project 2018–2020 “Coordination of autonomous unmanned vehicles for highly complex performances”.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The dynamic nature of quadrotor flight introduces significant uncertainty in system parameters, such as thrust and drag factors. Consequently, operators grapple with escalating challenges in implementing real-time control actions. This study presents an approach for estimating the dynamic model of Unmanned Aerial Vehicles based on Physics-Informed Neural Networks (PINNs), which is of paramount importance due to the presence of uncertain data and since control actions are required in very short computation times. In this regard, by including physical laws into neural networks, PINNs offer the potential to tackle several issues, such as heightened non-linearities in low-inertia systems, elevated measurement noise, and constraints on data availability or uncertainties, while ensuring the robustness of the solution, thus ensuring effective results in short time, once the network training has been performed and without the need to be retrained. The effectiveness of the proposed method is showcased in a simulation environment with real data and juxtaposed with a state-of-the-art technique, such as the Extended Kalman Filter (EKF). The results show that the proposed estimator outperforms the EKF both in terms of the efficacy of the solution and computation time.

Förderung

  • European Union Project ECSEL—Joint Undertaking RIA—2018 “Comp4Drones”
  • MAECI Project 2018–2020 “Coordination of autonomous unmanned vehicles for highly complex performances”

Zitieren

APA

Bianchi, D., Epicoco, N., Ferdinando, M. D., Gennaro, S. D., & Pepe, P. (2024). Physics-Informed Neural Networks for Unmanned Aerial Vehicle System Estimation. Drones, 8(12), 716. https://doi.org/10.3390/drones8120716

Vancouver

Bianchi D, Epicoco N, Ferdinando MD, Gennaro SD, Pepe P. Physics-Informed Neural Networks for Unmanned Aerial Vehicle System Estimation. Drones. 2024;8(12):716. doi:10.3390/drones8120716

BibTeX
@article{Bianchi2024,
  author = {Bianchi, Domenico and Epicoco, Nicola and Ferdinando, Mario Di and Gennaro, Stefano Di and Pepe, Pierdomenico},
  title = {Physics-Informed Neural Networks for Unmanned Aerial Vehicle System Estimation},
  journal = {Drones},
  year = {2024},
  volume = {8},
  number = {12},
  pages = {716},
  doi = {10.3390/drones8120716}
}
Kostenlos starten →