Context

Positioning systems such as the Global Positioning System (GPS) show limitations in non-line-of-sight environments leading to a disruption of location services in indoor environments. Many Indoor Positioning Systems (IPS) have been developed to tackle this limitation without achieving widespread adoption. Most existing IPS are expensive to deploy, offer poor performance or fail to guarantee user privacy. One promising solution is the use of decentralized and collaborative IPS.

Objectives

This project aims to develop a collaborative indoor positioning system that utilizes a network of devices to locate and track individuals within a building accurately. The system should use a decentralized approach by running the positioning algorithms on the devices. The goal is to deploy a decentralized IPS on campus by leveraging the sensors of the devices (inertial and wireless sensors) and the specificities of indoor environments.

Requirements

  • Solid programming skills, particularly in Python or Java or C/C++.
  • Good problem-solving skills and ability to work in a team environment
  • Ability to work independently and manage time effectively
  • Good written and oral communication skills.

### Hidden on the website: We are building a collaborative indoor positioning system that uses inertial measurement sensors on mobile devices. To improve the accuracy of our solution, we would like to leverage landmarks and proximity devices. For this project, the student will collect inertial data from a given environment. The goal is to extract useful information that could be used to reset the accumulation error from inertial-based ITS. Some of the information will be exchanged with nearby devices using a peer-to-peer approach. For the evaluation, the student should compare the results obtained with those from the state-of-the-art.

Contact

alpha.diallo@unil.ch