Localisation & tracking

In recent years, location-based information has become indispensable in multiple application domains including, amongst others, agriculture, healthcare, factory automation, warehousing, retails and logistics. To enable innovative indoor-localization applications, this research track focusses on three aspects: (i) localization system validation and benchmarking, (ii) multi-modal localization and (iii) scalability of localization solutions in harsh environments.

Localization system validation and benchmarking

Over the last few years, the number of indoor localization solutions has grown exponentially, and a wide variety of different technologies and approaches are being explored. Consequently, it is currently extremely hard to objectively compare the performance of multiple localization solutions with each other. To address the problem, we use large scale testbeds and in-situ measurements for automated evaluation and comparison of localization solutions in different environments using standardized ISO/IEC 18305 evaluation metrics, allowing unique insights in the overall localization system behavior in different conditions.

Fig. 3: Comparison of localization error distances of different technologies and algorithms in a hospital environment. A) Fingerprinting (Wi-Fi); B) Fingerprinting (BLE); C) Multi-lateral (Wi-Fi); D) Multi-lateral (BLE)
Comparison of localization error distances of different technologies and algorithms in a hospital environment. A) Fingerprinting (Wi-Fi); B) Fingerprinting (BLE); C) Multi-lateral (Wi-Fi); D) Multi-lateral (BLE)

Multi-modal localization 

Localization solutions often exhibit good performance in a subset of conditions. To cope with the inherent trade-offs of different localization approaches (e.g. in terms of energy consumption, accuracy, update ratio, etc.), multi-modal localization solutions combine multiple, heterogeneous localization approaches to improve overall performance. Some examples include the following.

  • Multimodal localization allows a smooth transition between indoor and outdoor by selecting the most appropriate network to perform the localization. Mid-range technologies can provide more accurate localization indoor, while long range technologies enable coverage outdoor. 
  • Infrastructure less localization approaches utilize pre-deployed devices rather than on-board calculations to localize devices. If the localization is handled by the network, the device itself can focus its resources on other tasks, saving energy when infrastructure is available, and switching to other approaches when necessary.

For this purpose, IEEE 802.15.4, Wi-Fi, BLE, DASH7, UWB and RFID are being used as enabling technologies, both with commercial hardware as specific designed prototypes.

Fig. 2: Multimodal Sigfox (868  Mhz)  / DASH7 (433 Mhz) prototype for fast localization algorithm validation.
Multimodal Sigfox (868  Mhz)  / DASH7 (433 Mhz) prototype for fast localization algorithm validation.

Scalability in harsh environments.

Localization solutions found in current scientific literature often analyze the performance using small scale experiments (only one mobile tag) in simple & unrealistic (often line-of-sight) conditions. As a result, there is currently a gap between many research efforts reported in scientific literature and the innovations that are required to cope with actual industry needs. A leap of knowledge is required to cope with the industry needs for improved scalability (e.g. density and coverage), for realizing these high accuracies in realistic environments and conditions, as well as to easily install and deploy localization solutions. To overcome these shortcomings, our research includes innovative beyond the state of the art solutions to

  • improve localization scalability and coverage to simultaneously localize hundreds of users in (indoor) areas of multiple square kilometers;
  • co-design localization & communication MAC protocols to combine multi-hop communication streams with localization capabilities;
  • support easy deployment and self-configuration of localization solutions;
  • provide accurate localization even during challenging activities (e.g. sporters, fireman, rescue operations, ...) and in harsh conditions (industrial environments with metal obstacles & interference);

Fig 1:  Automated benchmarking solutions are used for large scale testing and evaluation of the performance of localization solutions in different conditions (with and without external interference, office versus factory environment, etc.)
Automated benchmarking solutions are used for large scale testing and evaluation of the performance of localization solutions in different conditions (with and without external interference, office versus factory environment, etc.)

Projects

Key Publications

  • T. Van Haute, E. De Poorter, F. Lemic, V. Handziski, N. Wirstrym, T. Voigt, A. Wolisz and I. Moerman, “Platform for Benchmarking of RF-Based Indoor Localization Solutions”, IEEE Communications Magazine (Volume: 53, Issue: 9, September 2015)
  • T. Van Haute, E. De Poorter, I. Moerman, F. Lemic, V. Handziski, A. Wolisz, N. Wirstrom and T. Voigt, “Comparability of RF-based Indoor Localization Solutions in Heterogeneous Environments: An Experimental Study”, International Journal of Ad Hoc and Ubiquitous Computing, April 2015
  • T. Van Haute, B. Verbeke, E. De Poorter and I. Moerman, “Optimizing Time of Arrival Localization Solutions for Challenging Industrial Environments”, IEEE Transactions on Industrial Informatics, 2016
  • M. Aernouts, R. Berkvens, K. Van Vlaenderen, and M. Weyn, “Sigfox and LoRaWAN Datasets for Fingerprint Localization in Large Urban and Rural Areas,” Data, vol. 3, no. 2, p. 13, Apr. 2018.
  • S. Denis, R. Berkvens, B. Bellekens, and M. Weyn, “Large Scale Crowd Density Estimation Using a sub-GHz Wireless Sensor Network,” in 2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), 2018, pp. 849–855.
Staff

Involved faculty

Eli De Poorter & Maarten Weyn

Researchers