EUVIMEDEUVIMED entdecken
Crossref

Physics-informed online learning for velocity control of hydraulic excavators

Jakob Weber, Andreas Waldmann, Amadeus Lobe, Markus Gurtner, Ozan Demir, Benedikt Alt, Tobias Glück, Andreas Kugi

at - Automatisierungstechnik · 24.06.2026 · 74 (6) · 473-487

DOI: 10.1515/auto-2025-0106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift at - Automatisierungstechnik, online erschienen am 07.04.2026. Verfasst von Jakob Weber und 7 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hydraulic excavators remain among the least automated construction machines due to nonlinear hydraulics, varying environment interactions, and strict real-time requirements. We present a physics-informed online learning framework that provides a standardized velocity-level control interface, abstracting machine-specific hydraulics and enabling integration with higher-level automation. A physics-motivated base model is augmented with an online residual learner to compensate nonlinearities in real time. Experiments on a 12-ton excavator in leveling, grading, and a demanding 4-point cycle show substantial improvements over the base model alone: maximum absolute tracking error is reduced by up to 63 % in leveling and 70 % in the 4-point cycle, while RMSE is reduced by up to 54 % and 69 %.

Zitieren

APA

Weber, J., Waldmann, A., Lobe, A., Gurtner, M., Demir, O., Alt, B., Glück, T., & Kugi, A. (2026). Physics-informed online learning for velocity control of hydraulic excavators. at - Automatisierungstechnik, 74(6), 473-487. https://doi.org/10.1515/auto-2025-0106

Vancouver

Weber J, Waldmann A, Lobe A, Gurtner M, Demir O, Alt B, et al. Physics-informed online learning for velocity control of hydraulic excavators. at - Automatisierungstechnik. 2026;74(6):473-487. doi:10.1515/auto-2025-0106

BibTeX
@article{Weber2026,
  author = {Weber, Jakob and Waldmann, Andreas and Lobe, Amadeus and Gurtner, Markus and Demir, Ozan and Alt, Benedikt and Glück, Tobias and Kugi, Andreas},
  title = {Physics-informed online learning for velocity control of hydraulic excavators},
  journal = {at - Automatisierungstechnik},
  year = {2026},
  volume = {74},
  number = {6},
  pages = {473--487},
  doi = {10.1515/auto-2025-0106}
}
Kostenlos starten →