Visual-LiDAR SLAM with loop closure

Abstract: State-of-the-art LIDAR odometry techniques are exceptionally precise. However, while they solve the localization problem, they perform mapping on-the-run, not being able to close loops, neither re-localize in previously visited environments. This study is concerned with the development of a system that combines an accurate laser odometry estimator, with algorithms for place recognition in order to detect trajectory loops. This project uses widely available datasets from urban driving scenarios and outdoor areas for development and evaluation of the system The results obtained confirm that loop closure detection can significantly improve the accuracy and robustness of laser SLAM pipelines, with detectors based on point cloud segments and visual features displaying very strong performance during the evaluation phase.