首次用高斯点阵实现雷达多帧联合优化，大幅降低定位漂移。
RadarSplat-RIO: Indoor Radar-Inertial Odometry with Gaussian Splatting-Based Radar Bundle Adjustment
- 基于高斯点阵构建雷达密集场景表示，实现多帧联合优化
- 室内场景下平移误差减少90%，旋转误差减少80%
- 适合需要高精度定位的室内移动机器人应用
雷达在恶劣天气和光照条件下比视觉与激光雷达更稳定，但多数雷达SLAM仍依赖帧间里程计，导致显著漂移。虽然回环检测可纠正长期误差，但需重复经过相同位置且依赖鲁棒的场景识别。相比之下，视觉里程计通常利用束调整（BA）在局部窗口内联合优化位姿与地图。然而，雷达领域尚缺乏等效的BA方法。本文首次提出基于高斯点阵（GS）的雷达束调整框架，这是一种密集且可微分的场景表示。该方法利用完整的距离-方位-多普勒数据，联合优化雷达传感器位姿与场景几何结构，首次将多帧束调整的优势引入雷达系统。当与现有雷达惯性里程计前端结合时，显著降低位姿漂移并提升鲁棒性。在多个室内场景中，相比之前的方法，平均绝对平移误差降低90%，旋转误差降低80%。
原文摘要 · Abstract (English)
Radar is more resilient to adverse weather and lighting conditions than visual and Lidar simultaneous localization and mapping (SLAM). However, most radar SLAM pipelines still rely heavily on frame-to-frame odometry, which leads to substantial drift. While loop closure can correct long-term errors, it requires revisiting places and relies on robust place recognition. In contrast, visual odometry methods typically leverage bundle adjustment (BA) to jointly optimize poses and map within a local window. However, an equivalent BA formulation for radar has remained largely unexplored. We present the first radar BA framework enabled by Gaussian Splatting (GS), a dense and differentiable scene representation. Our method jointly optimizes radar sensor poses and scene geometry using full range-azimuth-Doppler data, bringing the benefits of multi-frame BA to radar for the first time. When integrated with an existing radar-inertial odometry frontend, our approach significantly reduces pose drift and improves robustness. Across multiple indoor scenes, our radar BA achieves substantial gains over the prior radar-inertial odometry, reducing average absolute translational and rotational errors by 90% and 80%, respectively.
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。