🤖 AI Summary
To address spurious loop closure matches in structurally repetitive indoor scenes with LiDAR, this paper proposes a descriptor-agnostic multi-frame loop closure verification method. It formulates loop closure decision-making as a truncated Sequential Probability Ratio Test (SPRT), adaptively accumulating temporal similarity evidence across multiple consecutive frames to enable accuracy-oriented dynamic decisions. This work is the first to introduce SPRT into LiDAR loop closure verification, eliminating reliance on specific feature descriptors and fixed ICP convergence thresholds. Evaluated on a five-sequence library dataset, the method significantly improves K-hit accuracy across various descriptors compared to single-frame and heuristic multi-frame baselines, while reducing absolute trajectory error (ATE) and relative pose error (RPE). It effectively mitigates loop closure ambiguity in challenging repetitive environments.
📝 Abstract
We propose a descriptor-agnostic, multi-frame loop closure verification method that formulates LiDAR loop closure as a truncated Sequential Probability Ratio Test (SPRT). Instead of deciding from a single descriptor comparison or using fixed thresholds with late-stage Iterative Closest Point (ICP) vetting, the verifier accumulates a short temporal stream of descriptor similarities between a query and each candidate. It then issues an accept/reject decision adaptively once sufficient multi-frame evidence has been observed, according to user-specified Type-I/II error design targets. This precision-first policy is designed to suppress false positives in structurally repetitive indoor environments. We evaluate the verifier on a five-sequence library dataset, using a fixed retrieval front-end with several representative LiDAR global descriptors. Performance is assessed via segment-level K-hit precision-recall and absolute trajectory error (ATE) and relative pose error (RPE) after pose graph optimization. Across descriptors, the sequential verifier consistently improves precision and reduces the impact of aliased loops compared with single-frame and heuristic multi-frame baselines. Our implementation and dataset will be released at: https://github.com/wanderingcar/snu_library_dataset.