NLOS Classification Based on RSS and Ranging Statistics Obtained from Low-Cost UWB Devices

Barral, Valentín; Escudero, Carlos J.; García-Naya, José A.

doi:10.23919/eusipco.2019.8902949

Cited by 32 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The measurement data obtained in both scenarios are available for the scientific community in [9,10], and they can be used to repeat and/or reproduce the experiments described in Section 5. More specifically, the data corresponding to the ML model-generation scenario, which is the same one considered in [5], were published in [9], whereas the data corresponding to the evaluation scenario are available in [10].…”

Section: Scenariosmentioning

confidence: 99%

See 1 more Smart Citation

Environmental Cross-Validation of NLOS Machine Learning Classification/Mitigation with Low-Cost UWB Positioning Systems

Barral

Escudero

García-Naya

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

Indoor positioning systems based on radio frequency inherently present multipath-related phenomena. This causes ranging systems such as ultra-wideband (UWB) to lose accuracy when detecting secondary propagation paths between two devices. If a positioning algorithm uses ranging measurements without considering these phenomena, it will face critical errors in estimating the position. This work analyzes the performance obtained in a localization system when combining location algorithms with machine learning techniques applied to a previous classification and mitigation of the propagation effects. For this purpose, real-world cross-scenarios are considered, where the data extracted from low-cost UWB devices for training the algorithms come from a scenario different from that considered for the test. The experimental results reveal that machine learning (ML) techniques are suitable for detecting non-line-of-sight (NLOS) ranging values in this situation.

show abstract

Section: Scenariosmentioning

confidence: 99%

“…Notice that the input features of the considered ML techniques have already been selected in a previous work [18]. More specifically, we chose as features the moving average (with a window of five measurements) of both ranging (µ ran ) and RSS (µ RSS ) obtained from the UWB devices.…”

Section: Machine Learning Techniquesmentioning

confidence: 99%

Environmental Cross-Validation of NLOS Machine Learning Classification/Mitigation with Low-Cost UWB Positioning Systems

Barral

Escudero

García-Naya

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such measurements were obtained from the measurement bank publicly available in [38], which was created by the authors from the experiment described in [39]. To fill this UWB measurement repository, a series of strategically placed Pozyx devices were employed to record measurements at different distances in three different situations (as shown in [40][41][42]):…”

Section: Uwb Simulatormentioning

confidence: 99%

Multi-Sensor Accurate Forklift Location and Tracking Simulation in Industrial Indoor Environments

et al. 2019

Self Cite

View full text Add to dashboard Cite

Location and tracking needs are becoming more prominent in industrial environments nowadays. Process optimization, traceability or safety are some of the topics where a positioning system can operate to improve and increase the productivity of a factory or warehouse. Among the different options, solutions based on ultra-wideband (UWB) have emerged during recent years as a good choice to obtain highly accurate estimations in indoor scenarios. However, the typical harsh wireless channel conditions found inside industrial environments, together with interferences caused by workers and machinery, constitute a challenge for this kind of system. This paper describes a real industrial problem (location and tracking of forklift trucks) that requires precise internal positioning and presents a study on the feasibility of meeting this challenge using UWB technology. To this end, a simulator of this technology was created based on UWB measurements from a set of real sensors. This simulator was used together with a location algorithm and a physical model of the forklift to obtain estimations of position in different scenarios with different obstacles. Together with the simulated UWB sensor, an additional inertial sensor and optical sensor were modeled in order to test its effect on supporting the location based on UWB. All the software created for this work is published under an open-source license and is publicly available.

show abstract

“…From such a set of measurements, some statistics are extracted and used as the features of interest in the classification and regression algorithms. All the measurement data are publicly available in [12] (Please refer to this article if you use these measurements).…”

Section: Introductionmentioning

confidence: 99%

NLOS Identification and Mitigation Using Low-Cost UWB Devices

Barral

Escudero

García-Naya

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

Indoor location systems based on ultra-wideband (UWB) technology have become very popular in recent years following the introduction of a number of low-cost devices on the market capable of providing accurate distance measurements. Although promising, UWB devices also suffer from the classic problems found when working in indoor scenarios, especially when there is no a clear line-of-sight (LOS) between the emitter and the receiver, causing the estimation error to increase up to several meters. In this work, machine learning (ML) techniques are employed to analyze several sets of real UWB measurements, captured in different scenarios, to try to identify the measurements facing non-line-of-sight (NLOS) propagation condition. Additionally, an ulterior process is carried out to mitigate the deviation of these measurements from the actual distance value between the devices. The results show that ML techniques are suitable to identify NLOS propagation conditions and also to mitigate the error of the estimates when there is LOS between the emitter and the receiver.

show abstract

NLOS Classification Based on RSS and Ranging Statistics Obtained from Low-Cost UWB Devices

Cited by 32 publications

References 8 publications

Environmental Cross-Validation of NLOS Machine Learning Classification/Mitigation with Low-Cost UWB Positioning Systems

Environmental Cross-Validation of NLOS Machine Learning Classification/Mitigation with Low-Cost UWB Positioning Systems

Multi-Sensor Accurate Forklift Location and Tracking Simulation in Industrial Indoor Environments

NLOS Identification and Mitigation Using Low-Cost UWB Devices

Contact Info

Product

Resources

About