This paper presents a state-of-the-art analysis on the methods suitable for vehicle indoor localization and exploiting the RFID (Radio Frequency IDentification) technology. The survey describes three ...main categories of vehicle localization systems: (i) solutions exploiting only the RFID technology, (ii) sensor-fusion techniques combining data from RFID systems and proprioceptive sensors, and (iii) sensor-fusion techniques combing RFID data with those of other exteroceptive sensors in addition to the RFID system itself. For each method, implementation and methodological details are discussed, by highlighting the applied RFID technology, namely passive HF-RFID, passive UHF-RFID, or any other RFID system. Also, the employed RFID parameters, i.e., tag EPC, RSSI or backscattered phase, are discussed. The survey focuses on the achievable localization performance, also accounting for infrastructure-deployment costs together with complexity and maintenance overhead. Positioning, tracking, navigation and simultaneous localization and mapping (SLAM) issues are here considered. The analysis highlights pros and cons of each method, together with the main challenges and perspectives of RFID-based solutions for vehicle localization.
The I-READ 4.0 project is aimed at developing an integrated and autonomous Cyber-Physical System for automatic management of very large warehouses with a high-stock rotation index. Thanks to a ...network of Radio Frequency Identification (RFID) readers operating in the Ultra-High-Frequency (UHF) band, both fixed and mobile, it is possible to implement an efficient management of assets and forklifts operating in an indoor scenario. A key component to accomplish this goal is the UHF-RFID Smart Gate, which consists of a checkpoint infrastructure based on RFID technology to identify forklifts and their direction of transit. This paper presents the implementation of a UHF-RFID Smart Gate with a single reader antenna with asymmetrical deployment, thus allowing the correct action classification with reduced infrastructure complexity and cost. The action classification method exploits the signal phase backscattered by RFID tags placed on the forklifts. The performance and the method capabilities are demonstrated through an on-site demonstrator in a real warehouse.
Autonomous vehicles enable the development of smart warehouses and smart factories with an increased visibility, flexibility and efficiency. Thus, effective and affordable localisation methods for ...indoor vehicles are attracting interest to implement real-time applications. This paper presents an Extended Kalman Smoother design to both localise a mobile agent and reconstruct its entire trajectory through a sensor-fusion employing the UHF-RFID passive technology. Extensive simulations are carried out by considering the smoother optimal-window length and the effect of missing measurements from reference tags. Monte Carlo simulations are conducted for different vehicle trajectories and for different linear and angular velocities to evaluate the method accuracy. Then, an experimental analysis with a unicycle wheeled robot is performed in real indoor scenario, showing a position and orientation root mean square errors of 15 cm, and 0.2 rad, respectively.
This article addresses the problem of determining the location of pallets carried by forklifts inside a warehouse, which are recognized thanks to an onboard Radio Frequency IDentification (RFID) ...system at the ultra-high-frequency (UHF) band. By reconstructing the forklift trajectory and orientation, the location of the pallets can be associated with the forklift position at the time of unloading events. The localization task is accomplished by means of an easy-to-deploy combination of onboard sensors, i.e., an inertial measurement unit (IMU) and an optical flow sensor (OFS), with a commercial ultra-wideband (UWB) system through an Unscented Kalman Filter (UKF) algorithm, which estimates the forklift pose over time. The proposed sensor fusion approach contributes to the localization error mitigation by preventing drifts in the trajectory reconstruction. The designed methos was at first evaluated by means of a simulation framework and then through an experimental analysis conducted in a large warehouse with a size of about 4000 m2.
Radio-frequency identification is one of the Internet of Things' most promising technologies and has been recently used in combination with mobile robots for logistics in business and retail ...applications. This manuscript deals with the localization of passive UHF RFID tags within industrial environments employing receiving antennas mounted on a mobile robot by using multilateration techniques that exploit narrowband phase-delay measurements. Two distinct Particle Filter approaches are presented to solve the 3D multilateration problem online and take advantage of a synthetic aperture created by the motion of the robot in the environment. One of the methods can operate in the presence of acquisition jumps since it does not rely on an unwrapping technique. Experimental results show promising performance concerning the recent literature. Moreover, the presented approach enables robust estimations concerning signal loss due to communication disturbances in noisy environments, typical of the industrial setting.
This paper presents and characterizes a measurement method for positioning of passive tags, by a drone equipped with a UHF-RFID reader. The method is based on a synthetic aperture radar approach and ...exploits the knowledge of the reader/drone trajectory, which is achieved with a differential Global Navigation Satellite System. Different sources of measurement uncertainty are analyzed by means of numerical simulations and experimental results. The method capabilities are discussed versus the length and shape of the reader trajectory. Finally, the proposed localization method is validated through an experimental analysis carried out with commercial RFID hardware and a microclass unmanned aerial vehicle.
This article presents a novel sensor-fusion method for indoor vehicle tracking. The phase of the signals backscattered by a set of Ultra High Frequency-Radio Frequency Identification (UHF-RFID) ...reference tags spread in the scenario is combined with the information acquired by on-board low-cost kinematic sensors. The RFID data are acquired by the on-board reader, during the relative motion of the vehicle with respect to the static reference tags, by resembling a synthetic-array approach, with an advantageous reduction of the reference-tag spatial density. In particular, such phase samples are combined with the kinematic data collected by odometers, through a sensor-fusion approach. The method capability is investigated through a numerical analysis that accounts for the main system parameters. Then, the tracking capability is demonstrated through a measurement campaign in a laboratory test set with a UHF-RFID robot prototype equipped with commercial encoders. Experimental results show an average localization error of centimeter order in the estimation of medium-length trajectories by employing only two reference tags in a relatively small area. The proposed method does not need for any calibration procedure and can be implemented by commercial off-the-shelf (COTS) hardware.
This paper introduces a new Radio Frequency Identification (RFID) gate for access control merging the benefits of Near-Field Focusing (NFF) and Deep Learning (DL). The gate uses a near-field focused ...antenna with a slight tilted beam to create an asymmetrical reading volume, which is essential to determine the direction of tag transit with a single antenna. The power and phase of the signal backscattered from the tag are used as features for classifying tag status: crossing, static, or moving around the gate yet not crossing it. The antenna is made up of a 3 × 3 array of circularly polarized resonant patches, operating at the ETSI RFID band (865-868 MHz). After validating the coverage volume of the antenna, tag data were used to train a multi-class Support Vector Machine (SVM) and a Long-Short Term Memory (LSTM) Neural Network (LSTM-NN). The appropriately sized LSTM-NN yields 98% classification accuracy in a scenario emulating a realistic shop entrance. The solution offers improved robustness to multipath effects and reduced false positives compared to conventional RFID gates using phased array antennas, two closely spaced portals, or bulky electromagnetic screens or absorbers, at lower cost and with a simpler infrastructure.
This article presents the application of the synthetic aperture radar (SAR) localization method for indoor positioning of ultrahigh-frequency (UHF)-radio frequency identification (RFID) tags when the ...robot-mounted reader antenna moves along multiple trajectories. By properly combining the phase data associated with a set of multiple paths, the whole length of the combined synthetic apertures enlarges, and then, the localization accuracy may improve. Besides, during consecutive inventory rounds, several tag position estimates are available, and they can be profitably combined to minimize the localization uncertainty. Different combination approaches are investigated to determine the best choice to improve the localization performance. The method capabilities are discussed through numerical analysis by considering different configurations of the multiple apertures and different measurement uncertainty sources. Finally, the proposed localization method is validated through an experimental analysis carried out with commercial RFID hardware and a robotic wheeled walker, in an indoor scenario, by employing different types of tags. The knowledge of the reader/robot trajectory required by the SAR method is here achieved with an optical system.
The phase of the signals backscattered by the ultrahigh frequency radio-frequency identification (UHF-RFID) tags is generally more insensitive to multipath propagation than the received signal ...strength indicator (RSSI). However, signal phase measurements are inherently ambiguous and could be further affected by the unknown phase offsets added by the transponders. As a result, the localization of an agent by using only signal phase measurements looks infeasible. In this article, it is shown instead that the design of a dynamic position estimator (e.g., a Kalman filter) based only on the signal phase measurement is actually possible. To this end, the necessary conditions to ensure the theoretical local nonlinear observability are first demonstrated. However, a system that is locally observable guarantees the convergence of the localization algorithm only if the actual initial agent position is approximately known a priori . Therefore, the second part of the analysis covers the global observability, which ensures convergence starting from any initial condition in the state space. It is important to emphasize that complete observability holds only in theory. In fact, measurement uncertainty may greatly affect position estimation convergence. The validity of the analysis and the practicality of this localization approach are further confirmed by numerical simulations based on an unscented Kalman filter (UKF).