The Design of a Vision-Assisted Dynamic Antenna Positioning Radio Frequency Identification-Based Inventory Robot Utilizing a 3-Degree-of-Freedom Manipulator
Sensors · 11.04.2025 · 25 (8) · 2418
DOI: 10.3390/s25082418 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 11.04.2025. Verfasst von Abdussalam A Alajami und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Communication Technologies Engineering, Pompeu Fabra University, 08002 Barcelona, Spain. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the “Interempresas Internacional” program of the Spanish CDTI.
Abstract (Originalsprache)
In contemporary warehouse logistics, the demand for efficient and precise inventory management is increasingly critical, yet traditional Radio Frequency Identification (RFID)-based systems often falter due to static antenna configurations that limit tag detection efficacy in complex environments with diverse object arrangements. Addressing this challenge, we introduce an advanced RFID-based inventory robot that integrates a 3-degree-of-freedom (3DOF) manipulator with vision-assisted dynamic antenna positioning to optimize tag detection performance. This autonomous system leverages a pretrained You Only Look Once (YOLO) model to detect objects in real time, employing forward and inverse kinematics to dynamically orient the RFID antenna toward identified items. The manipulator subsequently executes a tailored circular scanning motion, ensuring comprehensive coverage of each object’s surface and maximizing RFID tag readability. To evaluate the system’s efficacy, we conducted a comparative analysis of three scanning strategies: (1) a conventional fixed antenna approach, (2) a predefined path strategy with preprogrammed manipulator movements, and (3) our proposed vision-assisted dynamic positioning method. Experimental results, derived from controlled laboratory tests and Gazebo-based simulations, unequivocally demonstrate the superiority of the dynamic positioning approach. This method achieved detection rates of up to 98.0% across varied shelf heights and spatial distributions, significantly outperforming the fixed antenna (21.6%) and predefined path (88.5%) strategies, particularly in multitiered and cluttered settings. Furthermore, the approach balances energy efficiency, consuming 22.1 Wh per mission—marginally higher than the fixed antenna (18.2 Wh) but 9.8% less than predefined paths (24.5 Wh). By overcoming the limitations of static and preprogrammed systems, our robot offers a scalable, adaptable solution poised to elevate warehouse automation in the era of Industry 4.0.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information and Communication Technologies Engineering, Pompeu Fabra University, 08002 Barcelona, Spain.
ORCID-Profile: Abdussalam A Alajami, Rafael Pous
Förderung
- the “Interempresas Internacional” program of the Spanish CDTI
Zitieren
APA
Alajami, A. A., & Pous, R. (2025). The Design of a Vision-Assisted Dynamic Antenna Positioning Radio Frequency Identification-Based Inventory Robot Utilizing a 3-Degree-of-Freedom Manipulator. Sensors, 25(8), 2418. https://doi.org/10.3390/s25082418
Vancouver
Alajami AA, Pous R. The Design of a Vision-Assisted Dynamic Antenna Positioning Radio Frequency Identification-Based Inventory Robot Utilizing a 3-Degree-of-Freedom Manipulator. Sensors. 2025;25(8):2418. doi:10.3390/s25082418
BibTeX
@article{Alajami2025,
author = {Alajami, Abdussalam A and Pous, Rafael},
title = {The Design of a Vision-Assisted Dynamic Antenna Positioning Radio Frequency Identification-Based Inventory Robot Utilizing a 3-Degree-of-Freedom Manipulator},
journal = {Sensors},
year = {2025},
volume = {25},
number = {8},
pages = {2418},
doi = {10.3390/s25082418}
}
EUVIMED