Are you a student eager to apply your theoretical knowledge and fresh perspectives to real-world challenges? At Saab, we believe that innovation thrives on new ideas, and your master thesis project could be the spark that ignites our next technological breakthrough.
We recognize the immense value that students bring to our company. Your academic rigor, combined with your enthusiasm for cutting-edge technology, allows you to approach problems with a unique and insightful lens. At Saab, you’ll have the opportunity to collaborate with experienced engineers and specialists, gaining invaluable practical experience while making a tangible contribution to our growth and development.
Modern mission systems rely on information from multiple distributed sensors and platforms to establish a shared picture of the operational environment. In contested and dynamic environments, however, the information received from other sources cannot always be assumed to be reliable. Sensors may be degraded or misconfigured, communication and processing chains may introduce dependencies, and information may even be deliberately manipulated. Moreover, information exchanged between platforms may have been fused previously, creating correlations that are difficult to identify and account for.
Future autonomous and mission-critical systems therefore need data-fusion methods that consider not only the statistical uncertainty of information, but also their trustworthiness. Such methods should be able to identify and reduce the influence of unreliable information while retaining valid observations, adapt when source behavior changes, and provide an understandable basis for how information contributes to the resulting situational picture.
Description of the Thesis Project
The purpose of this thesis project is to investigate trust-aware distributed data fusion, with particular focus on the fusion of state estimates, or tracks, exchanged between multiple platforms. The student will investigate how the trustworthiness of sources and information can be estimated dynamically and how these trust estimates can be incorporated into distributed fusion algorithms. Important challenges include unknown correlations between estimates, time-varying source reliability, and distinguishing faulty or deceptive information from trustworthy but unexpected observations.