EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DigiHortiRobot: An AI-Driven Digital Twin Architecture for Hydroponic Greenhouse Horticulture with Dual-Arm Robotic Automation

Roemi Fernández, Eduardo Navas, Daniel Rodríguez-Nieto, Alain Antonio Rodríguez-González, Luis Emmi

Future Internet · 31.07.2025 · 17 (8) · 347

DOI: 10.3390/fi17080347 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 31.07.2025. Verfasst von Roemi Fernández und 4 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MICIU/AEI/10.13039/501100011033, Comunidad de Madrid a través de la Dirección General de Investigación e Innovación Tecnológica a través de la Orden 5696/2024, CSIC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of digital twin technology with robotic automation holds significant promise for advancing sustainable horticulture in controlled environment agriculture. This article presents DigiHortiRobot, a novel AI-driven digital twin architecture tailored for hydroponic greenhouse systems. The proposed framework integrates real-time sensing, predictive modeling, task planning, and dual-arm robotic execution within a modular, IoT-enabled infrastructure. DigiHortiRobot is structured into three progressive implementation phases: (i) monitoring and data acquisition through a multimodal perception system; (ii) decision support and virtual simulation for scenario analysis and intervention planning; and (iii) autonomous execution with feedback-based model refinement. The Physical Layer encompasses crops, infrastructure, and a mobile dual-arm robot; the virtual layer incorporates semantic modeling and simulation environments; and the synchronization layer enables continuous bi-directional communication via a nine-tier IoT architecture inspired by FIWARE standards. A robot task assignment algorithm is introduced to support operational autonomy while maintaining human oversight. The system is designed to optimize horticultural workflows such as seeding and harvesting while allowing farmers to interact remotely through cloud-based interfaces. Compared to previous digital agriculture approaches, DigiHortiRobot enables closed-loop coordination among perception, simulation, and action, supporting real-time task adaptation in dynamic environments. Experimental validation in a hydroponic greenhouse confirmed robust performance in both seeding and harvesting operations, achieving over 90% accuracy in localizing target elements and successfully executing planned tasks. The platform thus provides a strong foundation for future research in predictive control, semantic environment modeling, and scalable deployment of autonomous systems for high-value crop production.

Förderung

  • MICIU/AEI/10.13039/501100011033
  • Comunidad de Madrid a través de la Dirección General de Investigación e Innovación Tecnológica a través de la Orden 5696/2024
  • CSIC

Zitieren

APA

Fernández, R., Navas, E., Rodríguez-Nieto, D., Rodríguez-González, A. A., & Emmi, L. (2025). DigiHortiRobot: An AI-Driven Digital Twin Architecture for Hydroponic Greenhouse Horticulture with Dual-Arm Robotic Automation. Future Internet, 17(8), 347. https://doi.org/10.3390/fi17080347

Vancouver

Fernández R, Navas E, Rodríguez-Nieto D, Rodríguez-González AA, Emmi L. DigiHortiRobot: An AI-Driven Digital Twin Architecture for Hydroponic Greenhouse Horticulture with Dual-Arm Robotic Automation. Future Internet. 2025;17(8):347. doi:10.3390/fi17080347

BibTeX
@article{Fernndez2025,
  author = {Fernández, Roemi and Navas, Eduardo and Rodríguez-Nieto, Daniel and Rodríguez-González, Alain Antonio and Emmi, Luis},
  title = {DigiHortiRobot: An AI-Driven Digital Twin Architecture for Hydroponic Greenhouse Horticulture with Dual-Arm Robotic Automation},
  journal = {Future Internet},
  year = {2025},
  volume = {17},
  number = {8},
  pages = {347},
  doi = {10.3390/fi17080347}
}
Kostenlos starten →