Search papers, labs, and topics across Lattice.
3
0
2
3
Visual localization can achieve sub-centimeter accuracy, making it a viable alternative to GNSS for precise positioning tasks.
SE(3) alignment hides up to 76% of the absolute positioning error in RTK-SLAM, and this new dataset exposes the problem.
Self-supervision unlocks robust LiDAR global localization by learning scene-specific landmarks from BEV images, outperforming scene-agnostic methods.
