Off-Line Evaluation of Indoor Positioning Systems in Different Scenarios: The Experiences From IPIN 2020 Competition

Abstract

Every year, for ten years now, the IPIN competition has aimed at evaluating real-world indoor localisation systems by testing them in a realistic environment, with realistic movement, using the EvAAL framework. The competition provided a unique overview of the state-of-the-art of systems, technologies, and methods for indoor positioning and navigation purposes. Through fair comparison of the performance achieved by each system, the competition was able to identify the most promising approaches and to pinpoint the most critical working conditions. In 2020, the competition included 5 diverse off-site off-site Tracks, each resembling real use cases and challenges for indoor positioning. The results in terms of participation and accuracy of the proposed systems have been encouraging. The best performing competitors obtained a third quartile of error of 1 m for the Smartphone Track and 0.5 m for the Footmounted IMU Track. While not running on physical systems, but only as algorithms, these results represent impressive achievements.

A Survey of Recent Indoor Localization Scenarios and Methodologies

“…where |e i | = | ŷi − y i | defines the absolute error between the two vectors y and ŷ through time. Apart from these conventional definitions of errors, other indicators defined by ISO/IEC 18305 [123][124][125] are also drawing high research interests, namely EAG (i.e., error accumulation gradient) and CE (i.e., circular error). The evaluation of EAG is known as the error accumulation speed notably related to PDR [125].…”

“…Apart from these conventional definitions of errors, other indicators defined by ISO/IEC 18305 [123][124][125] are also drawing high research interests, namely EAG (i.e., error accumulation gradient) and CE (i.e., circular error). The evaluation of EAG is known as the error accumulation speed notably related to PDR [125]. The median of CE is commonly applied as an absolute error indicator compared with the ground truth position under 2D model localization [125], representing horizontal error magnitude [126].…”

“…The evaluation of EAG is known as the error accumulation speed notably related to PDR [125]. The median of CE is commonly applied as an absolute error indicator compared with the ground truth position under 2D model localization [125], representing horizontal error magnitude [126]. The ideal absolute position accuracy is up to 10 mm according to ISO/IEC 18305 [123,127].…”

GNSS-Free Outdoor Localization Techniques for Resource-Constrained IoT Architectures: A Literature Review

“…In this case, end nodes look for nearby localization systems with the short-range network interfaces and, eventually, switch to a long-range search [17]. The authors in [18] In different systems, a wide-area environment can contain many nodes that need to communicate throw a network and share the communication medium. For this reason, different technologies provide a range of communication options to handle network load to provide a scalable network.…”

“…Therefore, the LOS model is extended to incorporate the effect of the ground-reflected signal. That means, in the 2R model, the path-loss characteristics in LOS environments are dominated by interference between the direct path and the ground-reflected path [18]. In a more realistic system, the transmitted signal is obstructed by buildings, mountains, and foliage several times and a combination of these signals is received.…”