Research Analyzer
← Back ICRA 2026

OverlapMamba: A Shift State Space Model for LiDAR-Based Place Recognition

Jiehao Luo, Jintao Cheng, Qiuchi Xiang, Jin Wu, Rui Fan, Xieyuanli Chen, Xiaoyu Tang

PDF

AI summary

Key figure (auto-extracted from paper)
OverlapMamba delivers real-time, yaw-invariant LiDAR place recognition through a lightweight Mamba-based architecture with a novel stochastic SHIFT operation.
LiDAR Place Recognition Mamba Architecture State Space Models Loop Closure Detection Yaw Invariance Real-time SLAM

Problem

Existing LiDAR place recognition methods struggle to balance computational efficiency with robust yaw-invariant descriptor generation under viewpoint variations.

Approach

The method projects LiDAR point clouds into 1D range image sequences and processes them using a novel OverlapMamba block that combines bidirectional state space modeling with a stochastic SHIFT operation to efficiently capture spatial relationships and enforce rotational invariance.

Key results

  • Lightweight network producing high-quality yaw-equivariant features
  • Specialized OverlapMamba block maintaining linear computational complexity
  • Bidirectional and SHIFT strategies enhancing yaw invariance and generalization
  • Leading loop closure detection performance on KITTI, NCLT, and Ford Campus datasets

Why it matters

Provides a computationally efficient solution for real-time global localization and loop closure detection in resource-constrained autonomous navigation systems.

Abstract

Place recognition is the foundation for autonomous systems to achieve independent decision-making and secure operation. It is also crucial in tasks such as loop closure detection and global localization in Simultaneous Localization and Mapping (SLAM) technology. Existing LiDAR-based place recognition (LPR) methods use raw point cloud representations or multifarious point cloud representations as inputs, as well as employ convolutional neural networks or transformer archi- tectures. However, the recently proposed Mamba deep learning model combined with State Space Models (SSMs) has enor- mous potential in long sequence modeling. Therefore, we have developed a novel place recognition network OverlapMamba, which represents input range images as sequences. In a novel way, we use a stochastic reconstruction method to establish shifted state space models to compress the visual representa- tion. Extensive experiments on three public datasets demon- strate that OverlapMamba achieves competitive performance with real-time inference speed, which effectively detects loop closure even when traversing previously visited locations from different directions, indicating its strong place recognition ability and real-time efficiency. Our method has been implemented at http://github.com/SCNU-RISLAB/OverlapMamba.

Index terms

Localization Deep Learning for Visual Perception Computer Vision for Automation

Related papers