Din framtida utmaning
Radar is one of the most commonly used techniques for target acquisition. Under normal circumstances a radar is able to measure all three spatial coordinates, i.e., range, azimuth angle and elevation angle, to a target. In wartime this is in general no longer true mainly for two reasons: (i) the radar is jammed and is only able to measure the angles to a target, and (ii) the radar is intentionally run in passive mode to lower the electromagnetic signature of the own platform.
Moreover, military platforms, e.g., fighter aircraft, often use passive sensors such as infrared search and track (IRST) and radar warning receivers (RWR) that cannot directly measure range. For military operations it is therefore crucial to utilize the information extracted by angle-only measurements.
Target tracking is an estimation problem where targets are measured, predicted and tracked over time. Tracking targets using measurements where all spatial coordinates are observed is more or less straightforward. When dealing with angle-only measurements a common approach is to triangulate targets using two or more spatially separated sensors. New target tracks are then initiated in the intersections of the angle-only measurements originating from different sensors. Triangulation typically gives rise to ghost tracks which are tracks incorrectly initiated at triangulated points where there actually are no targets. In the multi-target case, angly-only target tracking becomes very complex due to the large number of potential ghost tracks.
Beskrivning av examensarbetet
In this master thesis work a multi-target tracking problem is studied. All sensor observations are angle-only measurements. The idea is to use machine learning (ML) algorithms to extract information about the targets of interest using the angle-only measurements.
A motivation for studying ML in this tracking problem is that ML has been shown to be powerful in many other similarly complex problems. An important part is to compare the considered ML methods with classical methods found within the target tracking domain. Handling of ghost tracks is crucial and is a natural measure of the performance of any proposed algorithm. Both the case with one sensor and multiple sensors will be handled.
Den du är idag
You are at the end of your master studies in engineering physics, electrical engineering or computer science. For a successful master thesis work, a strong background in mathematics and statistics is crucial. Programming experience and some basic knowledge in machine learning is also beneficial.
This position requires that you pass a security vetting based on the current regulations around/of security protection. For positions requiring security clearance additional obligations on citizenship may apply.
Vad du blir en del av
Saab is a leading defence and security company with an enduring mission, to help nations keep their people and society safe. Empowered by its 18,000 talented people, Saab constantly pushes the boundaries of technology to create a safer, more sustainable and more equitable world.
The Aeronautics business area is an innovative supplier of world-class aircraft systems, advanced aerostructures, and a wide range of support solutions within civil and military aviation. The business area researches, develops, and produces military aviation systems. We are building for the future through research and studies into innovative flight systems and the further development of our products.
The department Future Programs consist of the areas Concept design and Next generation studies, and is responsible for the execution of studies, contract, and projects for future capabilities and next generation products. The department is responsible for the execution of the Future Combat Air Systems (FCAS) program and some EU funded research projects within autonomy.
Kindly observe that this is an ongoing recruitment process and that the position might be filled before the closing date of the advertisement.
01-10-2022 – 01-12-2022
Tobias Olsson, Chef, 073-4184405
Robin Forsling, PhD-student, handledare, 073-4184178
Saab is a company with a strong people-orientation. We offer a friendly work environment where we support and help each other to be at our best. Continuous learning, career & talent development and employee well-being are examples of areas where we always put the strongest effort to offer great opportunities.