Lidar SLAM plays a significant role in mobile robot navigation and high-definition map construction. However, existing methods often face a trade-off between localization accuracy and system robustness in scenarios with a high proportion of dynamic objects, point cloud distortion, and unstructured environments. To address this issue, we propose a neural descriptors-based adaptive noise filtering strategy for SLAM, named ADA-DPM, which improves the performance of localization and mapping tasks through three key technical innovations. Firstly, to tackle dynamic object interference, we design the Dynamic Segmentation Head to predict and filter out dynamic feature points, eliminating the ego-motion interference caused by dynamic objects. Secondly, to mitigate the impact of noise and unstructured feature points, we propose the Global Importance Scoring Head that adaptively selects high-contribution feature points while suppressing the influence of noise and unstructured feature points. Moreover, we introduce the Cross-Layer Graph Convolution Module (GLI-GCN) to construct multi-scale neighborhood graphs, fusing local structural information across different scales and improving the discriminative power of overlapping features. Finally, experimental validations on multiple public datasets confirm the effectiveness of ADA-DPM.

翻译：激光雷达SLAM在移动机器人导航与高精地图构建中具有重要作用。然而，现有方法在动态物体比例较高、点云畸变及非结构化环境等场景下，往往面临定位精度与系统鲁棒性之间的权衡。为解决这一问题，我们提出了一种基于神经描述符的自适应噪声滤波策略用于SLAM，命名为ADA-DPM。该策略通过三项关键技术改进，提升了定位与建图任务的性能。首先，为应对动态物体干扰，我们设计了动态分割头（Dynamic Segmentation Head），用于预测并滤除动态特征点，消除动态物体引起的自身运动干扰。其次，为减轻噪声与非结构化特征点的影响，我们提出了全局重要性评分头（Global Importance Scoring Head），能够自适应地筛选高贡献度特征点，同时抑制噪声与非结构化特征点的影响。此外，我们引入了跨层图卷积模块（GLI-GCN），通过构建多尺度邻域图，融合不同尺度的局部结构信息，提升重叠特征的判别能力。最后，在多个公开数据集上的实验验证了ADA-DPM的有效性。