针对重复环境中的激光雷达回环误检问题，提出无需描述符的精准回环插入策略。
Query-Calibrated Segmental Admission for Descriptor-Agnostic LiDAR Loop Closure in Repetitive Environments
- 通过查询校准的分段评分机制，筛选几何可信的回环候选
- 在七类描述符上使回环因子减少3.8倍，精度提升至0.717
- 适合高重复性场景下的稳定SLAM系统，尤其适用于资源受限部署
结构重复环境会产生视觉上合理但存在混叠的激光雷达回环候选，若被错误引入位姿图优化将导致系统不稳定。本文提出查询校准的分段插入（QCSA）策略，一种不依赖描述符的稀疏回环插入方法，旨在提升图稳定性。该策略对短描述符段进行硬负样本评分，校准查询级别段落假设的几何一致性，并通过广义迭代最近点（G-ICP）验证后插入代表性回环对。在SNU图书馆数据集（SNULib）和HeLiPR重叠路线上的实验表明：在七类激光雷达描述符上，QCSA使插入的回环因子减少3.8倍，因子精度从0.542提升至0.717，显著降低每查询组的误插入数。在此更稀疏的图结构下，其平均绝对轨迹误差（ATE）与密集的Top1+G-ICP相当，最差序列的ATE则由1.064降至0.778米；整体均值与最差序列的ATE仍优于里程计基准。在相同因子预算下，其轨迹误差低于SeqSLAM与稀疏的Top1+G-ICP。HeLiPR上的固定迁移验证结果亦显示，无需路线特化调优即可有效抑制硬负例插入。这些结果验证了所提插入层在高混叠场景下的有效性。代码与数据集将于https://github.com/wanderingcar/snu_library_dataset发布。
原文摘要 · Abstract (English)
Structurally repetitive environments produce visually plausible but aliased LiDAR loop candidates that can destabilize pose-graph optimization when admitted as loop factors. We propose Query-Calibrated Segmental Admission (QCSA), a descriptor-agnostic sparse loop-admission policy for graph-stability-oriented insertion. The policy scores short descriptor segments against hard negatives, calibrates which query-level segment hypotheses reach geometry, and inserts representative pairs validated by Generalized Iterative Closest Point (G-ICP). We evaluate it on the SNU Library Dataset (SNULib) and HeLiPR overlap routes. Aggregated over seven LiDAR descriptor families on SNULib, QCSA reduces inserted loop factors by 3.8 times, raises factor precision from 0.542 to 0.717, and sharply lowers false admissions per query group. With this sparser graph, it maintains comparable mean absolute trajectory error (ATE) and substantially reduces worst-sequence ATE versus dense Top1+G-ICP, from 1.064 to 0.778 m. The aggregate mean and worst-sequence ATE remain lower than the odometry-only reference. Under a matched factor budget, QCSA also attains lower trajectory error than SeqSLAM and sparse Top1+G-ICP selections. Fixed-transfer validation on HeLiPR, with no route-specific tuning, likewise suppresses hard-negative admissions. These results support the proposed admission layer for aliasing-heavy simultaneous localization and mapping (SLAM). Our implementation and dataset will be released at: https://github.com/wanderingcar/snu_library_dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。