SLAM is an important capability for many autonomous systems, and modern LiDAR-based methods offer promising performance. However, for long duration missions, existing works that either operate directly the full pointclouds or on extracted features face key tradeoffs in accuracy and computational efficiency (e.g., memory consumption). To address these issues, this paper presents DFLIOM with several key innovations. Unlike previous methods that rely on handcrafted heuristics and hand-tuned parameters for feature extraction, we propose a learning-based approach that select points relevant to LiDAR SLAM pointcloud registration. Furthermore, we extend our prior work DLIOM with the learned feature extractor and observe our method enables similar or even better localization performance using only about 20\% of the points in the dense point clouds. We demonstrate that DFLIOM performs well on multiple public benchmarks, achieving a 2.4\% decrease in localization error and 57.5\% decrease in memory usage compared to state-of-the-art methods (DLIOM). Although extracting features with the proposed network requires extra time, it is offset by the faster processing time downstream, thus maintaining real-time performance using 20Hz LiDAR on our hardware setup. The effectiveness of our learning-based feature extraction module is further demonstrated through comparison with several handcrafted feature extractors.

翻译：同步定位与建图（SLAM）是许多自主系统的重要能力，而基于激光雷达的现代方法展现出优越的性能。然而，对于长时任务，现有方法无论是直接处理完整点云还是基于提取的特征，都面临着精度与计算效率（如内存消耗）之间的关键权衡。为解决这些问题，本文提出了DFLIOM系统，其中包含多项关键创新。与以往依赖人工设计启发式规则和手动调参进行特征提取的方法不同，我们提出了一种基于学习的方法，用于选择与激光雷达SLAM点云配准相关的点。此外，我们在先前工作DLIOM的基础上扩展了学习型特征提取器，并观察到我们的方法仅需使用稠密点云中约20%的点即可实现相当甚至更优的定位性能。我们在多个公开基准测试中验证了DFLIOM的优异表现，与最先进方法（DLIOM）相比，定位误差降低了2.4%，内存使用量减少了57.5%。尽管所提出的网络提取特征需要额外时间，但下游处理速度的提升抵消了这部分开销，从而在我们的硬件配置上使用20Hz激光雷达时仍能保持实时性能。通过与多种人工设计特征提取器的对比，进一步证明了我们基于学习的特征提取模块的有效性。