Researchers at the Massachusetts Institute of Technology (MIT), the University of Southern California, the University of Ferrara in Italy, and the Basque Center of Applied Mathematics in Spain have developed a system that helps networks of smart devices find their positions in environments where GPS usually fails.
In simulations of these "harsh" scenarios, the system operates significantly better than traditional methods, consistently performing near the theoretical limit for localization accuracy.
The method leverages many signal features and contextual information to create a probability distribution of all possible distances, angles, and other metrics.
The team used machine learning techniques to help the system learn a statistical model describing possible positions from measurements and contextual data.
Said MIT’s Moe Win, “Our soft information method is particularly robust in … harsh wireless environments.”
From MIT News
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA