Map Validation for Autonomous Driving Systems
Andrea Lucca Fabris · 2020
High-definition mapping is fundamental for self-driving vehicles. In this thesis we describe different approaches for online map validation whose goal is to verify if reality and map data are inconsistent. A probabilistic framework to perform the sensor fusion is defined and a spatial correlation is introduced to interpolate the information. The result is a probabilistic representation of the map whose assumed values represent the probability with which the map is valid in every point.