BioGraphLoc: Bio-Inspired Static Structure Graph for Robust LiDAR Global Localization
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-13
Abstract
Robust and accurate 6-DoF pose measurement in previously mapped environments is a cornerstone of autonomous systems, enabling tasks such as navigation, loop closure, and safety-critical decision-making. In large-scale urban or unstructured settings, Light Detection and Ranging (LiDAR)-based pose measurement has become increasingly vital due to its geometric fidelity and resilience to illumination or appearance changes. This paper presents BioGraphLoc, a novel bio-inspired measurement framework that determines global poses by extracting and encoding structural nodes from a Moving Object Segmentation (MOS)-filtered static structure graph, leveraging biologically inspired mechanisms such as place cells and head-direction cells. Specifically, we first construct a Spatial Static Topology Graph (StatiGraph) from mid-scale static clusters, and encode each node with a lightweight 4D FroZone descriptor that captures depth-level grouping, local geometry, and topology. For reliable correspondence detection, we introduce a Neural Activation Consistency (NAC) strategy and incorporate Hebbian-inspired memory updates to track node stability across time. The final 6-DoF pose is then measured via robust Truncated Least Squares (TLS) optimization with angular regularization. Experiments on the KITTI, HeLiPR, and our custom dataset demonstrate that the proposed method achieves state-of-the-art measurement accuracy, particularly excelling in structurally ambiguous and dynamically cluttered environments where traditional approaches often degrade, with the highest localization success rate reaching 91.32%.Keywords
Funding Information
- National Natural Science Foundation of China (62571074)
- National Natural Science Foundation of China (62201110)
- National Natural Science Foundation of China (CSTB2025NSCQ-LZX0142)
- National Natural Science Foundation of China (CSTB2023NSCQ-LZX0126)
- National Natural Science Foundation of China (CSTB2024NSCQ-LZX0123)
- Science and Technology Research Program of Chongqing Municipal Education Commission (KJQN202300615)
This publication has 45 references indexed in Scilit:
- DiffLoc: Diffusion Model for Outdoor LiDAR Localization2024
- Single-shot global localization via graph-theoretic correspondence matchingAdvanced Robotics, 2024
- SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization2023
- HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion2023
- Leveraging Equivariant Features for Absolute Pose Regression2022
- LiDAR-based localization using universal encoding and memory-aware regressionPattern Recognition, 2022
- OverlapNet: a siamese network for computing LiDAR scan similarity with applications to loop closing and localizationAutonomous Robots, 2021
- SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition2021
- PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition2018
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012