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.

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.

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.

No abstract

In the world of internet of things (IoT), obtaining the physical location of devices has always been a task of great interest for developing increasingly complex location-based services (LBS). That is why in recent years wireless communication standards have been incorporating new additions focused on providing localization mechanisms to technologies widely used in the IoT world, such as Wi-Fi or Bluetooth. In particular, the IEEE 802.11-2016 Wi-Fi standard introduced ranging estimation between two devices through the so-called fine time measurement (FTM) protocol, defined by the IEEE 802.11mc. FTM is not yet widespread in the IoT field, but commercial modules capable of offering this functionality at a reasonable price are starting to appear. In early 2021, the most widespread system on a chip (SOC) family among IoT devices, the ESP32-XX series, added support for this Wi-Fi standard, enabling, for the first time, the use of a standard designed for location-based systems. This paper analyzes the performance of this FTM implementation by carrying out and studying several measurement campaigns in different indoor and outdoor scenarios. Additionally, this work proposes an alternative real-time implementation for distance estimation inside the ESP32 using an approach based on machine learning. Such an implementation is successfully validated in a scenario totally different than those considered for the training and test sets. Finally, both the measurement sets and the developed software are available to the scientific community.