Offline-Online Hierarchical 3D Global Relocalization With Synthetic LiDAR Sensing and Descriptor-Space Retrieval

2026-05-08

AI Summary

This work addresses the computational inefficiency of existing global relocalization methods in large-scale 3D environments, where the vast pose search space hinders real-time performance. The authors propose a novel offline-online hierarchical framework: during the offline phase, LiDAR scans are synthesized from a grid-based map to construct an index of candidate locations and their geometric descriptors; in the online phase, a coarse pose is first retrieved efficiently in descriptor space, followed by point cloud registration to refine the estimate into an accurate 6-degree-of-freedom pose. By decoupling the search space into a preprocessing stage and a lightweight retrieval stage, the method achieves an average relocalization time of 3 seconds with 8 cm positioning accuracy in real-world scenarios—offering an order-of-magnitude improvement in computational efficiency over state-of-the-art approaches while maintaining comparable accuracy.

Abstract

3D global relocalization is one of the key capabilities for mobile robots in practical applications. However, in large scale spaces, existing methods often suffer from prolonged online relocalization time due to factors such as the massive pose search space and high computational overhead. To address these issues, this paper proposes an offline-online hierarchical framework that decouples the search space. In the offline phase, candidate positions and their corresponding geometric descriptor indices are generated in the map by simulating LiDAR scans within the grid map. In the online phase, a coarse pose estimate is first obtained via global retrieval, followed by point cloud registration to output precise 6-DoF pose estimates. Real-world experiments demonstrate that the proposed method achieves an average relocalization time of 3 s and an average localization accuracy of 8 cm in 3D environments. Compared with existing global relocalization methods, the proposed method achieves an order-of-magnitude improvement in computational efficiency while delivering comparable relocalization accuracy.

Problem

• 3D global relocalization
• large-scale environments
• computational efficiency
• pose search space
• online relocalization time

Innovation

• hierarchical relocalization
• synthetic LiDAR
• descriptor-space retrieval
• offline-online framework
• 3D global localization