the system can track a user’s location referenced to a map. Other techniques such as SmartLOCUS [157] and Cricket [158] also use a combination of RF and ultrasound technologies, where the TDoA between RF and ultrasound signals (generated by wall‐ and ceiling‐mounted beacons) is used to measure distance and localize mobile subjects.
Radianse [159] and Versus [160] use a combination of RF and IR signals to perform location positioning. Their tags emit IR and RF signals containing a unique identifier for each person or asset being tracked. The use of RF allows coarse‐grain positioning (e.g. floor level granularity), while the IR signals provide additional resolution (e.g. room granularity). The EIRIS local positioning system [161] uses an IRFID triple technology that combines IR, RF (UHF), and LF (RF low‐frequency transponder) signals. It combines the advantages of each technology, that is, the room location granularity of IR, the wide range of RF, and the tailored range sensitivity of LF.
The CUPID2.0 indoor positioning system [162] combines ToF‐based localization with signal strength information to improve indoor localization with Wi‐Fi RF signals. The proposed architecture consists of a location server and multiple Wi‐Fi APs, each of which talks to the mobile device. ToA‐based trilateration methods are used to determine the device location. In particular, the time of flight of the direct path (TFDP), as calculated from the data‐ACK exchange between the AP and the device, is used for distance estimation. TFDP is then combined with measurements of signal strength, particularly the EDP [82], to improve accuracy and also ensure scalability. The system was implemented, deployed, and analyzed at six cities across two different continents for more than 14 months with 40 different mobile devices and more than 2.5 million location fixes, and was shown to achieve a mean localization error of 1.8 m.
37.5.6.4 Techniques Fusing Dead Reckoning with Non‐RF Signals
A few indoor localization techniques combine inertial sensors with non‐RF signals. In [163], the IDyLL indoor localization system is proposed that combines dead reckoning with light measurements from photodiode sensors on smartphones. Typical luminaire sources (including incandescent, fluorescent, and LED) are often uniquely (sometimes evenly) spaced in many indoor environments. Moreover, most smartphones have light sensors (photodiodes) for automatic brightness adjustment that can theoretically sample at a high rate (e.g. 1.17 MHz for APDS‐9303 on Nexus 5 and 7 devices), although they are often constrained either by the hardware interface or the OS‐level support to a few hertz to up to 100 Hz. IDyLL samples the light sensors at 10 Hz, and uses an illumination peak detection algorithm to gather light readings. The readings are combined with those obtained from inertial sensors, as well as knowledge of the floor map and luminary placement, to achieve fine‐grained indoor localization. The approach in [164] combines dead reckoning, laser scanners, and image‐based localization, all integrated in a human‐carried backpack which can be used to generate 3D models of complex indoor environments. The locations are determined from data capture based on two laser scanners and an inertial measurement unit. The localization performance could be improved by making use of camera images that have been taken in an offline phase. The images can be used to refine the six parameters of the camera pose and improve the quality of the 3D textured model.
37.6 Open Research Issues
Indoor localization systems are steadily becoming more mature, but there are still several challenges that must be addressed, as outlined in [165], which discusses the experiences and lessons learned from Microsoft’s indoor localization competition. Below we provide a holistic overview of some of the key open research challenges in the area of indoor localization.
Evaluation methodologies. The outcomes of studies to determine the efficacy of an indoor localization solution can be impacted by several factors, such as the building type and size, construction materials and layout along the analyzed indoor paths, lengths of the indoor paths, characteristics of test subjects, and the test procedure followed (including duration and the degree of “natural” activity) [126]. There is currently very little consensus on how to evaluate various indoor localization solutions, which hinders an appropriate comparison. Because of stark differences in the above‐listed factors (that are also not often clearly presented) across evaluation studies, claims made in literature about the accuracy of a particular solution are often difficult to reproduce. Many solutions in literature are content with a very simple proof‐of‐concept evaluation, with contrived walking tests along indoor locales that are limited in scope (e.g. testing with a single subject). Moreover, manually evaluating indoor localization technologies is a tedious and time‐consuming process. It may be possible to reduce evaluation overhead with an automated robot‐based benchmarking platform that can also improve the fidelity of the evaluation process.
Evaluation metrics. Indoor localization solutions in the literature are compared using various metrics such as the average location error, RMSE, 95th percentile, and so on. However these metrics often do not capture real‐world variations. For instance, [165] discussed how certain indoor locales were very easy to localize by even the simplest of techniques; however, some other points were extremely difficult to accurately localize. The way in which evaluation points are selected and weighted in the evaluation metric is therefore crucial, and a lot of work needs to be done in terms of standardizing the evaluation metrics of indoor localization technologies to properly capture these parameters.
Sensor positioning. Many indoor localization techniques rely on readings from sensors that are carried by the person or object to be tracked. It is possible for the orientation and position of the sensors to change over time and across tracked subjects; for example, a person may carry a smartphone with inertial sensors in different pockets, or hold it in their hand when moving. There may also be other types of positioning issues; for example, the direction a smartphone is facing may be different from the direction the subject is moving. Indoor localization techniques should take such factors into account and compensate for positioning variations. For better accuracy in the estimation of the step length or even the heading direction, it may be preferable to use foot‐mounted sensors [166]; however, this usually comes at the cost of user inconvenience.
Sensor calibration. Many of the sensors used for indoor localization have an inherent bias and variations in sensitivity to environmental factors. In particular, the low‐cost and compact MEMS inertial sensors found in smartphone IMUs have inferior sensor screening, installation error calibration, cross axis error calibration, zero point correction, temperature drift compensation, and so on, compared to the more accurate (and thus bulkier and more expensive) IMUs used in unmanned aerial vehicles (UAVs) and other industrial applications [138]. The IMU sensors must therefore be individually re‐calibrated when in use, to avoid drifts in outputs that result in increasing errors over time.
Battery power. Indoor localization techniques that rely on mobile devices carried by moving subjects need to be aware of the battery life constraints of the device. If excessive computation or sensing is performed with the mobile device, the battery of the mobile device can drain quickly, and this is an extremely undesirable scenario, especially if it happens during navigation. For example, if smartphones are utilized for indoor localization, care should be taken to limit the use of CPU, GPU, or DSP processing; wireless radio modules (e.g. Wi‐Fi, 4G/5G cellular, GPS); and inertial sensors, as all of these when used continuously or in combination can cause the smartphone battery to drain very quickly. Techniques to optimize energy efficiency in mobile devices [167–170] will be key to achieving cost‐effective and practical indoor localization solutions.
Processing capability and memory constraints. Many indoor localization techniques rely on algorithms that must be run on resource‐constrained mobile devices carried by the moving subject. For example, many techniques require the use of machine learning algorithms, image processing, signal processing, bandpass filters, peak detectors, autocorrelators or particle filters, and so on. In general, mobile devices have limited computational capabilities, and therefore algorithms
