At IDLab, we leverage wireless communication links for localisation and tracking Internet of Things devices, and for sensing the environment. Since our targeted IoT applications are typically using power constrained sensors or asset trackers, our research is often on energy aware localisation and tracking. Hence, we are targeting the perfect trade-off between application requirements, localisation accuracy and energy usage.

We have identified three distinct topics, that focus on use-case specific trade-offs:

  • Multimodal Localisation & Tracking: Combining multiple technologies to support a wide variety of use-cases and environments in a single device.
  • Device Free Sensing: Sensing where people are located, without equipping them with a tracking device.
  • Context-aware Localisation & Sensing: Improving location estimates of classic systems by taking into account context information of the device.

Research examples

  • Multimodal Localisation & Tracking: We use whatever wireless communication technology is available on the device and in the environment to provide the best suitable location estimate depending the application.  When inside, we can use private networks such DASH7, Bluetooth, Wi-Fi or UWB. When outsides, we can use GNSS if both the signal and the required power is available; otherwise, we resolve to LoRaWAN, Sigfox, NB-IoT or cellular based localisation. 
  • Device Free Sensing: We estimate the location of people or the size of groups of people without requiring a connection with their devices or requiring them to carry any device at all. We either use a network of wireless devices that we install in the environment, or sense (without processing) signals that are available in the area anyway, such as cellular or Wi-Fi. One of our typical testing environments are festivals or other large gatherings, where we estimate the size of the crowd. However, we are also estimating smaller numbers of people or even the location of individuals in city or office environments, either by our own wireless sensor network or by passively processing the ubiquitous wireless signals in the environment. 
  • Context-aware Localisation & Sensing: We leverage information that we have about the environment to improve location estimates. For example, when we know that a car will drive into a tunnel, we make sure that location updates are calculated by 5G or Wi-Fi 802.11p roadside units. Or we use the constraints posed by shipping containers to enable self-localisation of wireless devices attached to those containers.

A selection of publications

  • ​Aernouts Michiel, Lemic Filip, Moons Bart, Famaey Jeroen, Hoebeke Jeroen, Weyn Maarten, Berkvens Rafael (2020) A multimodal localization framework design for IoT applications. Sensors 20:16.
  • Bni Lam Noori, Tanghe Emmeric, Steckel Jan, Joseph Wout, Weyn Maarten (2020) ANGLE : ANGular Location Estimation Algorithms. IEEE access.
  • Janssen Thomas, Berkvens Rafael, Weyn Maarten (2020) Benchmarking RSS-based localization algorithms with LoRaWAN. Internet of Things
  • Denis Stijn, Kaya Abdil, Berkvens Rafael, Weyn Maarten (2020) Device-free localization and identification using sub-GHz passive radio mapping. Applied Sciences.
  • Singh Ritesh Kumar, Pappinisseri Puluckul Priyesh, Berkvens Rafael, Weyn Maarten (2020) Energy consumption analysis of LPWAN technologies and lifetime estimation for IoT application. Sensors.
  • Denis Stijn, Bellekens Ben, Kaya Abdil, Berkvens Rafael, Weyn Maarten (2020) Large-scale crowd analysis through the use of passive radio sensing networks. Sensors.
  • Denis Stijn, Bellekens Ben, Weyn Maarten, Berkvens Rafael (2020) Sensing thousands of visitors using radio frequency. IEEE Systems journal / IEEE systems council

A selection of projects

Involved faculty

Maarten Weyn