GNSS-Augmented LiDAR SLAM for Accurate Vehicle Localization in Large Scale Urban Environments

Although accurate and reliable localization is a prerequisite for autonomous driving, in urban environments neither the Global Navigation Satellite System (GNSS) nor the Simultaneous Localization and Mapping (SLAM) ensure satisfying results in terms of both local accuracy and global consistency. Hence, we contribute in this paper a method to augment the existing LiDAR-based SLAM systems with GNSS measurements, applying the factor graph formulation of the problem. We contribute a tightly coupled GNSS/LiDAR SLAM considering constraints from LiDAR and GNSS measurements, and propose a filtering procedure to cope with GNSS measurements that introduce non-Gaussian noise. We evaluate our approach on the challenging UrbanNav dataset, considering different LiDAR SLAM algorithms and different GNSS receivers, and showing that our solution outperforms previous approaches to GNSS/LiDAR integration.