Date of Award
Computer and Information Science
Indoor localization is a modern problem of computer science that has no unified solution, as there are significant trade-offs involved with every technique. Magnetic localization, though less popular than WiFi signal based localization, is a sub-field that is rooted in infrastructure-free design, which can allow universal setup. Magnetic localization is also often paired with probabilistic programming, which provides a powerful method of estimation, given a limited understanding of the environment. This thesis presents Minet, which is a particle filter based localization system using the Earth's geomagnetic field. It explores the novel idea of state space limitation as a method of optimizing a particle filter, by limiting the scope of possibilities the filter has to predict. Minet is also built as a distributed model, which can be easily modified to integrate new technologies. Minet showed promising results, but ultimately fell short of its accuracy goal. Minet had some inconsistencies that led to these accuracy issues, but these issues have been diagnosed and can be fixed in future updates. Finally, potential improvements of Minet's base components are discussed, along with how different technologies such as a Deep Learning model can be implemented to improve performance.
Drake, Michael, "Minet Magnetic Indoor Localization" (2020). Honors Theses. 1495.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.