ABOUT THIS POSITION

Society has become heavily dependent on Position, Navigation and Time (PNT) information derived from Global Navigation Satellite Systems (GNSS). These systems provide accurate estimates of position and time, but are vulnerable to interference due to their weak signal strengths. In military contexts, this poses a significant threat to operational effectiveness. Military personnel on foot are particularly challenged in GNSS-denied environments. Fall-back navigation methods such as maps and compasses are time-consuming and error-prone. Additionally, strict SWaP (size, weight & power) constraints are critical, as soldiers carry all equipment. Light-weight software-enhanced GNSS-denied PNT solutions are therefore vital, and a point of focus for the PNT team.

We offer two master’s thesis level internship assignments:

• Modelling locomotion using neural networks: Recent literature has demonstrated the use of neural network approaches for modelling walking displacements using low-cost hardware in controlled conditions. The military context is more challenging: soldiers walk, run, sneak, crouch or walk sideways over every terrain imaginable. The goal is to explore and improve data-driven modelling in the military context to make high-quality models for any condition.
• Magnetic Navigation in Buildings: Upon entering buildings, GNSS and other navigation techniques seize working. Recent literature has shown that magnetic sensors can pick up local characteristics of steel structures in constructions. This allows SLAM algorithms to build up a map that can be used for navigation. This assignment focuses on modelling these local magnetic fields efficiently and validating these models through experiments.

You will perform this assignment in the PNT team, part of the Autonomous Systems & Robotics department. We are a passionate, dedicated and tightly-knit team with extensive knowledge of multi-agent systems, system architectures, software engineering, information fusion, artificial intelligence and robotics.