Deep Learning Enables Robust Drone-based UHF-RFID Localization in Warehouses

Li, Chenglong; Tanghe, Emmeric; Suanet, Pieter; David, Paul A.; Hoebeke, Jeroen; Martens, Luc; Poorter, Eli De; Joseph, Wout

doi:10.23919/at-ap-rasc54737.2022.9814319

Cited by 6 publications

(6 citation statements)

References 12 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably the tag/antenna displacement trajectories can be taken into account in training the algorithms. For example, [36] performs unwrapping using a random forest algorithm and [41] proposes a deep learning approach, reaching accuracies between 0.5 m and 0.1 m.…”

Section: A Complex Rolling Window Unwrappingmentioning

confidence: 99%

RFID Landslide Monitoring: Long-Term Outdoor Signal Processing and Phase Unwrapping

Charléty

Breton²,

Baillet

et al. 2023

IEEE J. Radio Freq. Identif.

View full text Add to dashboard Cite

Localization of passive Radio-Frequency Identification (RFID) tags has been used to monitor landslide surface displacement since 5 years. This method, applied on slow displacements lower than 1cm per day, allows a high spatiotemporal resolution at a relatively low cost. With the feedback of the previous years, this paper proposes to summarize the various challenges encountered with the long-term outdoor RFID localization method, and presents data-processing solutions that were implemented to overcome these challenges. We propose a complex-smoothing unwrapping algorithm, a multi-frequency merging operation, as well as multi-tag and multi-antenna phase combining method. The concept of an unwrapping reference guide is presented and applied with groups of tags showing coherent displacements, or with absolute reference measurements. These approaches allow a higher data availability up to 38% for one site over multiple years, and a better phase unwrapping. Earth surface displacement monitoring with RFID proves to be a robust and accurate solution, with four equipped sites across France and Switzerland.

show abstract

Section: A Complex Rolling Window Unwrappingmentioning

confidence: 99%

RFID Landslide Monitoring: Long-Term Outdoor Signal Processing and Phase Unwrapping

Charléty

Breton²,

Baillet

et al. 2023

IEEE J. Radio Freq. Identif.

View full text Add to dashboard Cite

show abstract

“…Consequently, the CIR of the signal changes due to different environmental effects [31]. These patterns in the signal generated by different environments can be learned by a neural network [32]. In this work, the raw CIR data are collected from nine different sites in Ghent, Belgium.…”

Section: B Data Collectionmentioning

confidence: 99%

Toward Seamless Localization: Situational Awareness Using UWB Wearable Systems and Convolutional Neural Networks

Kia

David

Herbruggen

et al. 2023

J. Ind. Sea. Pos. Nav.

Self Cite

View full text Add to dashboard Cite

“…The integration of RFID technology with drones has shown promising results in enhancing inventory control and supply chain management. Li et al (2021) established a passive RFID localization scheme based on drones for inventory management in warehouses, demonstrating the potential of this technology in real-world applications [17]. Furthermore, Turkler et al (2022) highlighted the use of drones carrying RFID readers for dynamic inventory checks in factory environments, emphasizing the practicality of this approach in industrial settings [18].…”

Section: Introductionmentioning

confidence: 99%

“…With RFID systems, companies would have increased product visibility, reduce out-of-stock items, trim warehouse costs, eliminate stock errors, reduce theft and shrinkage, and allow companies to regularly update their logistics and inventory databases. Furthermore, Li et al (2022) investigated drone-based RFID localization for fast and accurate inventory management [17]. The literature has also discussed the potential of drones to provide valuable information for inventory tracking and management in various industries, including construction projects.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Radio Frequency Identification Power and Unmanned Aerial Vehicle Altitude in Plant Inventory Applications

Patiluna,

Maja,

Robbins

2024

AgriEngineering

View full text Add to dashboard Cite

In the business of growing and selling ornamental plants, it is important to keep track of plants from nursery to distribution. Radio Frequency Identification (RFID) technology provides an easier tracking method for inventories of plants by attaching tags with unique identifiers. Due to the vast area of most nurseries, there is a need to have an efficient method of scanning RFID tags. This paper investigates the use of drones and RFID, specifically, the effects of RFID reader power and flight altitude on tag counts. The experimental setup evaluated three RFID reader power levels (15 dBm, 20 dBm, and 27 dBm), three flight altitudes (3 m, 5 m, and 7 m), the number of passes (one or two), and two plant types (‘Green Giant’ arborvitae and ‘Sky Pencil’ holly). For RFID tags, four types were used (L5, L6, L8, and L9), with two antenna types (dog-bone and square-wave) and two attachment types (loop-lock and stake). For each power level, the UAV was flown to three different altitudes of 3 m, 5 m, and 7 m above the ground. At each altitude, two scan passes were performed at a constant speed of approximately 1.5 m/s. Each plot of plants (two in total) was randomly tagged with a total of 40 RFID tags per plot. Field data were collected from September to December 2023 (on a total of eight dates). The data showed that a power level of 15 dBm and an altitude of 3 m yielded a tag count of 53%, while counts of 34% and 16% were achieved at 5 m and 7 m, respectively. At 20 dBm and an altitude of 3 m, the count accuracy across all tag types and both plants was 90%. When the altitude was increased to 5 m and 7 m, tag-count accuracy dropped to 75% and 33%, respectively. The highest count accuracy was observed at 27 dBm and an altitude of 3 m, with a reading accuracy of 98%. Tag types L6 and L9 performed better at any power level and altitude, while L5 and L8 performed well at a higher power level and lower altitude. In this experiment, canopy properties (size and shape) had no effect on the number of tags read. This study aimed to evaluate the RFID power and UAV altitude achieving the highest accuracy in scanning the RFID tags. Furthermore, it also assessed the effects of plant growth on the scanning efficiency and accuracy of the system.

show abstract

Deep Learning Enables Robust Drone-based UHF-RFID Localization in Warehouses

Cited by 6 publications

References 12 publications

RFID Landslide Monitoring: Long-Term Outdoor Signal Processing and Phase Unwrapping

RFID Landslide Monitoring: Long-Term Outdoor Signal Processing and Phase Unwrapping

Toward Seamless Localization: Situational Awareness Using UWB Wearable Systems and Convolutional Neural Networks

Evaluation of Radio Frequency Identification Power and Unmanned Aerial Vehicle Altitude in Plant Inventory Applications

Contact Info

Product

Resources

About