Scholarlink

<p>Dynamic content in traffic scenes can significantly affect LiDAR-Inertial Simultaneous Localization and Mapping (SLAM). Robust or maximum-likelihood formulations can attenuate inconsistent returns, but when motion is not explicitly modeled, challenges remain. Dynamic motion disrupts scan registration and mapping, leading to ghosting artifacts and a degradation in global map quality. To address this, we propose a dual-stage SLAM framework that constructs a visibility-consistent static subset. The first stage performs multi-resolution range-image differencing and applies visibility-aware incidence-angle correction to restore grazing-angle ground points that are often misclassified. The second stage conducts cluster-level reclassification to eliminate residual dynamics and recover static structures. The refined static points are fused within a tightly coupled factor graph using IMU pre-integration, scan-context loop closure, and a static-prior factor. Odometry features are visibility-gated and confidence-weighted to improve correspondence reliability in dynamic traffic conditions. Evaluations on the UrbanLoco and a self collected dynamic traffic dataset demonstrate up to 11.9% lower trajectory error and visibly cleaner static maps compared with state-of-the-art baselines. The results confirm that our method achieves more stable registration and long-term map fidelity in highly dynamic urban environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Dual-Stage LiDAR-Inertial SLAM with Hierarchical Dynamic Object Removal in Dynamic Environments

  • 期刊论文

  • 发表日期：

    2026年4月7日

查看全文
  • Xiao Yang,
  • Baicang Guo,
  • Lisheng Jin,
  • Yewei Shi,
  • Hongyu Zhang,
  • Hao Liu,
  • Xingchen Liu

摘要

Dynamic content in traffic scenes can significantly affect LiDAR-Inertial Simultaneous Localization and Mapping (SLAM). Robust or maximum-likelihood formulations can attenuate inconsistent returns, but when motion is not explicitly modeled, challenges remain. Dynamic motion disrupts scan registration and mapping, leading to ghosting artifacts and a degradation in global map quality. To address this, we propose a dual-stage SLAM framework that constructs a visibility-consistent static subset. The first stage performs multi-resolution range-image differencing and applies visibility-aware incidence-angle correction to restore grazing-angle ground points that are often misclassified. The second stage conducts cluster-level reclassification to eliminate residual dynamics and recover static structures. The refined static points are fused within a tightly coupled factor graph using IMU pre-integration, scan-context loop closure, and a static-prior factor. Odometry features are visibility-gated and confidence-weighted to improve correspondence reliability in dynamic traffic conditions. Evaluations on the UrbanLoco and a self collected dynamic traffic dataset demonstrate up to 11.9% lower trajectory error and visibly cleaner static maps compared with state-of-the-art baselines. The results confirm that our method achieves more stable registration and long-term map fidelity in highly dynamic urban environments.