RING plus plus : Roto-Translation-Invariant Gram for Global Localization on a Sparse Scan Map

Global localization plays a critical role in many robot applications. LiDAR-based global localization draws the community's focus with its robustness against illumination and seasonal changes. To further improve the localization under large viewpoint differences, we propose RING++ that has roto-translationinvariant representation for place recognition and global convergence for both rotation and translation estimation. With the theoretical guarantee, RING++ is able to address the large viewpoint difference using a lightweight map with sparse scans. In addition, we derive sufficient conditions of feature extractors for the representation preserving the roto-translation invariance, making RING++ a framework applicable to generic multichannel features. To the best of our knowledge, this is the first learning-free framework to address all the subtasks of global localization in the sparse scan map. Validations on real-world datasets show that our approach demonstrates better performance than state-ofthe-art learning-free methods and competitive performance with learning-based methods. Finally, we integrate RING++ into a multirobot/session simultaneous localization and mapping system, performing its effectiveness in collaborative applications.

Automated summary

Global localization is crucial in robot applications, and LiDAR-based global localization stands out for its robustness against illumination and seasonal changes. We propose RING++, a learning-free framework with roto-translation-invariant representation and global convergence for rotation and translation estimation, which can address large viewpoint differences using a lightweight map with sparse scans. Our approach, the first of its kind, accomplishes all subtasks of global localization in sparse scan maps and outperforms state-of-the-art learning-free methods, competing with learning-based methods.