4D millimeter-wave (mmWave) radars are sensors that provide robustness against adverse weather conditions (rain, snow, fog, etc.), and as such they are increasingly used for odometry and SLAM (Simultaneous Location and Mapping). However, the noisy and sparse nature of the returned scan data proves to be a challenging obstacle for existing registration algorithms, especially those originally intended for more accurate sensors such as LiDAR. Following the success of 3D Gaussian Splatting for vision, in this paper we propose a summarized representation for radar scenes based on global simultaneous optimization of 3D Gaussians as opposed to voxel-based approaches, and leveraging its inherent probability distribution function for registration. Moreover, we propose tackling the problem of radar noise by optimizing multiple scan matching hypotheses in order to further increase the robustness of the system against local optima of the function. Finally, following existing practice we implement an Extended Kalman Filter-based Radar-Inertial Odometry pipeline in order to evaluate the effectiveness of our system. Experiments using publicly available 4D radar datasets show that our Gaussian approach is comparable to existing registration algorithms, outperforming them in several sequences.

翻译：四维毫米波雷达是一种能够在恶劣天气条件（雨、雪、雾等）下保持鲁棒性的传感器，因此正日益广泛地应用于里程计与同步定位与建图任务。然而，雷达扫描数据固有的噪声与稀疏特性对现有配准算法构成了严峻挑战，特别是那些最初为激光雷达等更精确传感器设计的算法。受三维高斯溅射在视觉领域成功的启发，本文提出一种基于三维高斯全局同步优化的雷达场景摘要表示方法（区别于基于体素的方法），并利用其固有的概率分布函数进行配准。此外，我们通过优化多组扫描匹配假设来解决雷达噪声问题，从而进一步提升系统对函数局部最优解的鲁棒性。最后，遵循现有实践，我们实现了基于扩展卡尔曼滤波的雷达-惯性里程计流程以评估系统性能。在公开四维雷达数据集上的实验表明，我们的高斯建模方法在性能上与现有配准算法相当，并在多个数据序列中表现更优。