Passionate about making ideas a reality? Join our welcoming world of tech and let your ideas soar.
Background
The situational picture provided by modern surveillance radars contains a wide range of targets - including military and civilian aircrafts, missiles and projectiles of different types, small objects such as UAVs and birds, as well as different types of ground-based targets -- often occurring in dense configurations and complex background environments. This presents a major challenge characterized by the need for target models that have high predictive capabilities, at the same time as being able to describe a wide behavioral envelope. Unfortunately, highly expressive models necessarily become highly nonlinear, mandating the use of computationally expensive particle filters for state estimation. This has historically been a significant roadblock limiting the practical use of such models - a problem that possibly could be alleviated by the advent of differentiable particle filters, providing a path towards system identification with highly optimized filters.
Project description
The goal of the project is to explore and evaluate the viability of differentiable particle filters to establish a data-driven paradigm for system identification and filter optimization suited for targets originating from a behaviorally diverse envelope, where target type is a priori unknown. In a differentiable particle filter, neural networks are used to parameterize the system model and proposal distribution. The project involves investigating different possibilities for these parameterizations. This could for example involve normalizing flows, but also other model-structures that are relevant for the application at hand. An important precondition for a successful model-structure is the possibility to obtain tractable importance weights for flexible parameterizations of the proposal distribution for the particle filter.
Your profile
You are in the end of your technical master's education in Engineering Physics, Engineering Mathematics, or similar, with an interest in mathematics and numerical methods. Courses in Stochastic analysis, Bayesian statistics, and Nonlinear filtering are meriting, as well as practical experience of deep learning.
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.
What you will be part of
Behind our innovations stand the people who make them possible. Brave pioneers and curious minds. Everyday heroes and inventive troubleshooters. Those who share deep knowledge and those who explore sky-high. And everyone in between.
Joining us means making an impact together, contributing in our own unique ways. From crafting complex code and building impressive defence and security solutions to simply sharing a coffee with a colleague, every action counts. We encourage you to take on challenges, to create smart inventions and grow in our friendly and tech-savvy workspace. We have a solid mission to keep people and society safe.
Saab is a leading defence and security company with an enduring mission, to help nations keep their people and society safe. Empowered by its 22,000 talented people, Saab constantly pushes the boundaries of technology to create a safer and more sustainable world.
Saab designs, manufactures and maintains advanced systems in aeronautics, weapons, command and control, sensors and underwater systems. Saab is headquartered in Sweden. It has major operations all over the world and is part of the domestic defence capability of several nations. Read more about us here
Contact information
Therese Lundberg, Manager