Pieter Suanet

Pieter Suanet

Auto-generated profile, based on publicly available information

Pieter Suanet

Aucxis CVBA, Stekene, Belgium

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 March 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
CLChenglong Li
Chenglong Li
ETEmmeric Tanghe
Emmeric Tanghe
PSPieter Suanet
Pieter Suanet
DPDavid Plets
David Plets
JHJeroen Hoebeke
Jeroen Hoebeke
Wout JosephWout Joseph
Wout Joseph
Radio frequency identification (RFID) technology attracts extensive attention for industrial applications, especially supply chain businesses and inventory management. In this article, a passive RFID localization scheme based on unmanned aerial vehicles (UAVs) or drones is established for inventory management in warehouses. In case of the major challenge of the on-board antenna tracking errors in practical scenarios, the state-of-the-art (SOTA) numerical methods rely on accurate antenna positions, such as synthetic aperture radar (SAR)-based algorithms, which will introduce large positioning errors and become unreliable. To this end, we propose a new relative RFID localization method based on phase, received signal strength indicator (RSSI), and readability, which is little affected by antenna tracking errors. In the proposed method, the tagged items on the racks are located laterally through pinpointing the minimum of the unwrapped phases, which have been unwrapped based on the hybrid random forest (RF) model. RSSI differences and the read count of each patch antenna's beam are utilized to distinguish the rack level of tagged assets via a boosting tree classifier. The experimental results in a real warehouse show that the proposed method achieves 27.1-cm mean lateral positioning accuracy and orders the tagged items horizontally and vertically with more than 96.7% and 98.0% accuracy, respectively.

1 March 2020
Verified
Conference Paper
Open access
CLChenglong Li
Chenglong Li
ETEmmeric Tanghe
Emmeric Tanghe
DPDavid Plets
David Plets
PSPieter Suanet
Pieter Suanet
NPNico Podevijn
Nico Podevijn
Wout JosephWout Joseph
Wout Joseph