Positioning by Road Feature Correspondence

Tyson Demarest, University of Rhode Island


This research analyzes a new method to localize a moving vehicle within a known road network using differential odometry and a digital road map. The technique proposes geometrically hashing road features whose curvature is great enough to represent a distinct, measurable, real-world phenomenon. Several other strategies using road map data to constrain a localization search are discussed. In the recognition phase, this research proposes using a modified particle filter provides a way to maintain, test, and resample multiple hypotheses of the vehicle's dead-reckoned location.

Subject Area

Computer science

Recommended Citation

Tyson Demarest, "Positioning by Road Feature Correspondence" (2018). Dissertations and Master's Theses (Campus Access). Paper AAI10785480.