Mapping and evaluation for GPS restricted environments used for automated parking applications

In this paper, two state-of-the-art solutions to the simultaneous localization and mapping (SLAM) problem are implemented, depending on the environment type. A line feature-based solution using the extended Kalman filter is selected for structured environments, while for unstructured an incremental likelihood maximization algorithm using scan matching is adopted. This work proposes an evaluation method for the mapping accuracy assessment, able to handle results from different map representations. The resulting maps of both algorithms are compared to the digitalized areas blueprints after being converted to a common representation, which makes use of custom elements supported by the popular OpenStreetMap digital map format. Experiments were performed in two parking garages with different characteristics showing the applicability of the proposed evaluation method independent of the SLAM algorithm used.