skip to main content


Title: UHF RFID tag localization using pattern reconfigurable reader antenna
Passive ultra high frequency (UHF) radio frequency identification (RFID) tags have the potential to find ubiquitous use in indoor object tracking, localization, and contact tracing. We propose a machine learning-based method for RFID indoor localization using a pattern reconfigurable UHF RFID reader antenna array. The received signal strength indicator (RSSI) values (from 10,000 tags) recorded at the reader antenna units are used as features to evaluate the machine learning models with a train-test split of 75%-25%. The training and testing data is generated by a wireless ray tracing simulator. Five machine learning models: random forest regressor, decision tree regressor, Nu support vector regressor, k nearest regressor, and kernel ridge regressor are compared. Random forest regressor has the lowest localization error both in terms of average Euclidean distance (AED) and root-mean-square error (RMSE). For random forest regressor, localization error results show that 90% of the tags are within 1 meter of their true position, and 67% are within 50 cm of their true position based on Euclidean distance.  more » « less
Award ID(s):
1816387
NSF-PAR ID:
10355674
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
2022 IEEE 22nd Annual Wireless and Microwave Technology Conference (WAMICON)
Page Range / eLocation ID:
1 to 4
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. UHF RFID tags have been widely used for contactless inventory and tracking applications. One fundamental problem with RFID readers is their limited tag reading rate. Existing RFID readers (e.g., Impinj Speedway) can read about 35 tags per second in a read zone, which is far from enough for many applications. In this paper, we present the first-of-its-kind RFID reader (mReader), which borrows the idea of multi-user MIMO (MU-MIMO) from cellular networks to enable concurrent multi-tag reading in passive RFID systems. mReader is equipped with multiple antennas for implicit beamforming in downlink transmissions. It is enabled by three key techniques: uplink collision recovery, transition-based channel estimation, and zero-overhead channel calibration. In addition, mReader employs a Q-value adaptation algorithm for medium access control to maximize its tag reading rate. We have built a prototype of mReader on USRP X310 and demonstrated for the first time that a two-antenna reader can read two commercial off-the-shelf (COTS) tags simultaneously. Numerical results further show that mReader can improve the tag reading rate by 45% compared to existing RFID readers. 
    more » « less
  2. null (Ed.)
    Passive radio-frequency identification (RFID) tags are attractive because they are low cost, battery-free, and easy to deploy. This technology is traditionally being used to identify tags attached to the objects. In this paper, we explore the feasibility of turning passive RFID tags into battery-free temperature sensors. The impedance of the RFID tag changes with the temperature and this change will be manifested in the reflected signal from the tag. This opens up an opportunity to realize battery-free temperature sensing using a passive RFID tag with already deployed Commercial Off-the-Shelf (COTS) RFID reader-antenna infrastructure in supply chain management or inventory tracking. However, it is challenging to achieve high accuracy and robustness against the changes in the environment. To address these challenges, we first develop a detailed analytical model to capture the impact of temperature change on the tag impedance and the resulting phase of the reflected signal. We then build a system that uses a pair of tags, which respond differently to the temperature change to cancel out other environmental impacts. Using extensive evaluation, we show our model is accurate and our system can estimate the temperature within a 2.9 degree centigrade median error and support a normal read range of 3.5 m in an environment-independent manner. 
    more » « less
  3. Currently, there is an increasing interest in the use of RFID systems with passive or battery-less tags with sensors incorporated, also known as computational RFID (CRFID) systems. These passive tags use the reader signal to power up their microcontroller and an attached sensor. Following the current standard EPC C1G2, the reader must identify the tag (receive the tag's identification code) prior to receive data from its sensor. In a typical RFID scenario, several sensor tags share the reader interrogation zone, and during their identification process, their responses often collide, increasing their identification time. Therefore, RFID application developers must be mindful of tag anti-collision protocols when dealing with CRFID tags in dense RFID sensor networks. So far, significant effort has been invested in simulation-based analysis of the performance of anti-collision protocols regarding the tags identification time. However, no one has explored the experimental performance of anti-collision protocols in an RFID sensor network using CRFID. This paper: (i) demonstrates that the impact of one tag identification time over the total time required to read one sensor data from that same tag is very significant, and (ii) presents an UHF-SDR RFID system which validates the improvement of FuzzyQ, a fast anticollision protocol, in relation to the protocol used in the current RFID standard. 
    more » « less
  4. In this work, we present a battery-less wireless Micro-Electro-Mechanical (MEMS)-based respiration sensor capable of measuring the respiration profile of a human subject from up to 2 m distance from the transceiver unit for a mean excitation power of 80 µW and a measured SNR of 124.8 dB at 0.5 m measurement distance. The sensor with a footprint of ~10 cm2 is designed to be inexpensive, maximize user mobility, and cater to applications where disposability is desirable to minimize the sanitation burden. The sensing system is composed of a custom UHF RFID antenna, a low-loss piezoelectric MEMS resonator with two modes within the frequency range of interest, and a base transceiver unit. The difference in temperature and moisture content of inhaled and exhaled air modulates the resonance frequency of the MEMS resonator which in turn is used to monitor respiration. To detect changes in the resonance frequency of the MEMS devices, the sensor is excited by a pulsed sinusoidal signal received through an external antenna directly coupled to the device. The signal reflected from the device through the antenna is then analyzed via Fast Fourier Transform (FFT) to extract and monitor the resonance frequency of the resonator. By tracking the resonance frequency over time, the respiration profile of a patient is tracked. A compensation method for the removal of motion-induced artifacts and drift is proposed and implemented using the difference in the resonance frequency of two resonance modes of the same resonator. 
    more » « less
  5. null (Ed.)
    Accurate precise positioning at millimeter wave frequencies is possible due to the large available bandwidth that permits precise on-the-fly time of flight measurements using conventional air interface standards. In addition, narrow antenna beamwidths may be used to determine the angles of arrival and departure of the multipath components between the base station and mobile users. By combining accurate temporal and angular information of multipath components with a 3- D map of the environment (that may be built by each user or downloaded a-priori), robust localization is possible, even in non-line-of-sight environments. In this work, we develop an accurate 3-D ray tracer for an indoor office environment and demonstrate how the fusion of angle of departure and time of flight information in concert with a 3-D map of a typical large office environment provides a mean accuracy of 12.6 cm in line-of-sight and 16.3 cm in non-line-of-sight, over 100 receiver distances ranging from 1.5 m to 24.5 m using a single base station. We show how increasing the number of base stations improves the average non-line-of-sight position location accuracy to 5.5 cm at 21 locations with a maximum propagation distance of 24.5 m. Index Terms—localization; positioning; position location; navigation; mmWave; 5G; ray tracing; site-specific propagation; map-based 
    more » « less